Paper Citation Record · LEDGER

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

As of 11 August 2026, this Paper Citation Record lists 66 of 66 outbound references and 100 inbound Pith citation observations for arXiv:2211.00593.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2211.00593 v1

Coverage vector

measured 66 of 66 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-05-13T17:13:51.408311Z

measured 166 of 166 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-10T06:31:04.303077+00:00

measured 100 of 137 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-10T22:18:23.641247Z

measured 1 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-08-05T02:28:24.338817Z

Reference resolution

66 of 66 outbound references displayed

verified exact13
verified fuzzy38
unresolved4
parse uncertain1
malformed identifier0
metadata mismatch10

External citation measurements

50
pith, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 98497d3c-b10e-453e-bf8d-596debd99853 · outbound

This paper cites Language models are few-shot learners.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Language models are few-shot learners

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.545755Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f08b166d-a709-4013-bfc6-bfdd73254e67 · outbound

This paper cites A literature survey of recent advances in chatbots.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small A literature survey of recent advances in chatbots

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.549189Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 37bfacbe-9204-4eb2-bea1-7d8fd4956da3 · outbound

This paper cites A mathematical framework for transformer circuits.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small A mathematical framework for transformer circuits

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.550951Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 279f0de2-acd0-49f9-a6b9-22cbb44214f2 · outbound

This paper cites Causal abstractions of neural networks.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Causal abstractions of neural networks

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.552747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9f534c03-5115-4764-b4f2-8f1ad9c98b99 · outbound

This paper cites X-Risk Analysis for AI Research.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small X-Risk Analysis for AI Research

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.482305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2c858597-b301-4dc6-906d-460d218ead17 · outbound

This paper cites Natural language descriptions of deep visual features.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Natural language descriptions of deep visual features

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.554390Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a30b5c23-be6f-47a9-a6e5-036ea59af1d5 · outbound

This paper cites Are sixteen heads really better than one? Advances in neural information processing systems, 32.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Are sixteen heads really better than one? Advances in neural information processing systems, 32

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.556608Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e7b7134a-9388-4c94-94a5-4c1dc9906e5f · outbound

This paper cites Compositional explanations of neurons.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Compositional explanations of neurons

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.558173Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation dd0c2e2d-b8be-4964-881f-6ac73b41eef2 · outbound

This paper cites A mechanistic interpretability analysis of grokking.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small A mechanistic interpretability analysis of grokking

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.559969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 403d4df1-c521-44a9-b835-c04f501e2754 · outbound

This paper cites Mechanistic interpretability, variables, and the importance of interpretable bases.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Mechanistic interpretability, variables, and the importance of interpretable bases

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.561992Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f8d5f64c-cf8f-4a71-8f2a-54eba66d1f20 · outbound

This paper cites Distill , year =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Distill , year =

Reference 16

Resolution: metadata mismatch; doi, observed 2026-05-13T17:13:51.448603Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f436f922-3967-4911-80db-da477de89f2e · outbound

This paper cites Language models are unsupervised multitask learners.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Language models are unsupervised multitask learners

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.564180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aca4400f-afb2-45ac-a7bb-c249b2619fb9 · outbound

This paper cites Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.504124Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a96bd0e0-3982-45cb-93ba-5e824f313142 · outbound

This paper cites Attention is all you need.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Attention is all you need

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.566263Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3169fad0-860b-48ac-b990-01b8e1e848e4 · outbound

This paper cites Investigating gender bias in language models using causal mediation analysis.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Investigating gender bias in language models using causal mediation analysis

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.568214Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0cd3606-387a-4966-b84e-6cd3416991a9 · outbound

This paper cites Emergent Abilities of Large Language Models.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Emergent Abilities of Large Language Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-13T17:13:51.497753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4e3bd3c9-e00a-434a-a5a9-f123127dc550 · outbound

This paper cites Shifting machine learning for healthcare from development to deployment and from models to data.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Shifting machine learning for healthcare from development to deployment and from models to data

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.569974Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 17f4ee92-3301-4a0c-8146-1327c7c89752 · outbound

This paper cites Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.442503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2d3a1646-5ffe-4ddb-a530-9b526f550ba3 · outbound

This paper cites BERT Rediscovers the Classical NLP Pipeline.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small BERT Rediscovers the Classical NLP Pipeline

Reference 25

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.446046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3d26bd71-74cf-4a5d-8c6c-369a06076975 · outbound

This paper cites 2019 , subtitle =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small 2019 , subtitle =

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.571557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation bf0796bc-9d44-4fb9-8347-a1754cf14598 · outbound

This paper cites Learning to Generate Reviews and Discovering Sentiment.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Learning to Generate Reviews and Discovering Sentiment

Reference 27

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.452248Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation cd5c7a01-5b11-47d7-8b76-2285a6854c9a · outbound

This paper cites Implicit Representations of Meaning in Neural Language Models.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Implicit Representations of Meaning in Neural Language Models

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.455778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a175f726-d97d-4094-8d9e-db3489192e8d · outbound

This paper cites An Interpretability Illusion for BERT.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small An Interpretability Illusion for BERT

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.507126Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7a387258-f02b-4a01-ae25-77cd1a6846ed · outbound

This paper cites Proceedings of the 57th Conference of the Association for Computational Linguistics.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Proceedings of the 57th Conference of the Association for Computational Linguistics

Reference 30

Resolution: verified exact; doi, observed 2026-05-13T17:13:51.458733Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 68a0559c-f58b-49cf-9553-2b7f506d0b5a · outbound

This paper cites International Conference on Machine Learning , pages=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small International Conference on Machine Learning , pages=

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.573549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 02091e11-3423-48e0-ae27-57225f28dfd2 · outbound

This paper cites Unveiling Transformers with LEGO: a synthetic reasoning task.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Unveiling Transformers with LEGO: a synthetic reasoning task

Reference 32

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.491461Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fbc2d07d-597a-42d0-9b66-0e56c0f3a6b1 · outbound

This paper cites Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit

Reference 33

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.494465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7f3fa369-c0d2-41a8-bb75-9482dfaf0adc · outbound

This paper cites arXiv , year=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small arXiv , year=

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.575342Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a4280cf2-37d2-4e9a-88ec-6d2c4dd77aa7 · outbound

This paper cites In-context Learning and Induction Heads.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small In-context Learning and Induction Heads

Reference 35

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T17:13:51.501018Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0820cd9-5070-49fe-8f27-45396e23d4e7 · outbound

This paper cites Information , volume=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Information , volume=

Reference 36

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.577082Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5d100709-e2bc-449b-963f-4322db7bd8d1 · outbound

This paper cites Nature Biomedical Engineering , pages=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Nature Biomedical Engineering , pages=

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.578696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 63ae8442-2c60-4ab8-a8bd-741f909d8abd · outbound

This paper cites ArXiv , year=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small ArXiv , year=

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.580503Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0f9dba28-98ec-4cc6-96b0-f2beed018285 · outbound

This paper cites Unsolved Problems in ML Safety.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Unsolved Problems in ML Safety

Reference 39

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T20:45:28.030299Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 83cfc6fa-cb3e-40e9-8621-b986875ff7cd · outbound

This paper cites International Conference on Learning Representations , year=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small International Conference on Learning Representations , year=

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.582070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 44a715b7-5696-4efb-bead-36a3fdf5c9d2 · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Advances in Neural Information Processing Systems , volume=

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.583817Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0bd8dc7d-0387-4449-b96d-a2ae2a04cfad · outbound

This paper cites Implicit Representations of Meaning in Neural Language Models.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Implicit Representations of Meaning in Neural Language Models

Reference 42

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.479376Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a1cb9589-f8aa-417a-9e46-03544b49338a · outbound

This paper cites Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Proceedings of the IEEE/CVF International Conference on Computer Vision , pages=

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.585785Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 91650fe7-4249-4906-8bf1-82e44e07705b · outbound

This paper cites Advances in Neural Information Processing Systems , volume=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Advances in Neural Information Processing Systems , volume=

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.587697Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 602f23f7-0f08-449c-adc1-1ddda406da47 · outbound

This paper cites On the Pitfalls of Analyzing Individual Neurons in Language Models.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small On the Pitfalls of Analyzing Individual Neurons in Language Models

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.467058Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2ee3c801-d141-4173-bcaa-57024fc6ff31 · outbound

This paper cites Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Causal Analysis of Syntactic Agreement Mechanisms in Neural Language Models

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.473392Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 88621bf4-43d0-4af1-a283-d2ae7a49a5bf · outbound

This paper cites ArXiv , year=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small ArXiv , year=

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.509351Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 047ba2cb-c305-4d86-96f3-3e6a46377144 · outbound

This paper cites Advances in neural information processing systems , volume=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Advances in neural information processing systems , volume=

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.511277Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c7072732-3db9-4ae0-b905-d61d79902e7f · outbound

This paper cites Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks

Reference 49

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.437696Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ffe00a29-866d-49e0-b687-5fcbbec3926f · outbound

This paper cites Analyzing Transformers in Embedding Space.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Analyzing Transformers in Embedding Space

Reference 50

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.476307Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ea483a46-26a0-4d1f-82c7-33a2bd8eaa54 · outbound

This paper cites Transformer Feed-Forward Layers Are Key-Value Memories.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Transformer Feed-Forward Layers Are Key-Value Memories

Reference 51

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T23:35:50.837220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 3ec52625-53b6-4a57-98cb-bfecf08c22ed · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Locating and Editing Factual Associations in GPT

Reference 52

Resolution: metadata mismatch; arxiv_id, observed 2026-05-16T09:58:57.694057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2eeb5839-af2f-4a12-b879-b8301d1766ea · outbound

This paper cites Distill , year =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Distill , year =

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.513258Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation aa4caf6d-a2c5-4beb-9462-bd4c3efeed6d · outbound

This paper cites Scaling Learning Algorithms Towards.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Scaling Learning Algorithms Towards

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.515215Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0bb6b7e6-a66e-430a-84ca-5f5a148e293f · outbound

This paper cites and Osindero, Simon and Teh, Yee Whye , journal =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small and Osindero, Simon and Teh, Yee Whye , journal =

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.517180Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c4d53185-b7e1-4f5e-a6d2-c3c023af842a · outbound

This paper cites 2016 , publisher=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small 2016 , publisher=

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.519294Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 25fd0f4f-fec7-4df4-9f3a-f64fef9fc1cc · outbound

This paper cites an unresolved cited work.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Unresolved cited work

Reference 57

Resolution: unresolved; raw_fallback, observed 2026-05-13T17:13:51.521096Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 62c4ebf3-4e48-4c0a-9285-de5df982d558 · outbound

This paper cites 2021 , journal=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small 2021 , journal=

Reference 58

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.523060Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c0987cb3-bed0-4b35-99b5-fc5ddbc65541 · outbound

This paper cites an unresolved cited work.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Unresolved cited work

Reference 59

Resolution: unresolved; raw_fallback, observed 2026-05-13T17:13:51.524818Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f4af84f0-fff2-4cdd-8fff-2ac8df776418 · outbound

This paper cites Advances in Neural Information Processing Systems , editor=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Advances in Neural Information Processing Systems , editor=

Reference 60

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.526724Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b18e8659-7b93-4b86-9abe-7341cee8e46c · outbound

This paper cites Advances in Neural Information Processing Systems , description =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Advances in Neural Information Processing Systems , description =

Reference 61

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.528723Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0cc76915-2cdf-4107-bcab-6983442b219a · outbound

This paper cites Language Models are Few-Shot Learners , url =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Language Models are Few-Shot Learners , url =

Reference 62

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.530521Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5991bd5f-0b1f-47cf-b598-1d91be5347a0 · outbound

This paper cites Distill , year =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Distill , year =

Reference 63

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.532356Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b0c57649-e011-4981-a64d-b48d65a89eb4 · outbound

This paper cites an unresolved cited work.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Unresolved cited work

Reference 64

Resolution: unresolved; raw_fallback, observed 2026-05-13T17:13:51.534412Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c482a09a-28d9-46ee-ab98-a981aff2145a · outbound

This paper cites Sanity Checks for Saliency Maps , url =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Sanity Checks for Saliency Maps , url =

Reference 65

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.537065Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1d6857b2-b1d1-47bb-a8fd-528a0afa2dc3 · outbound

This paper cites GitHub repository , howpublished =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small GitHub repository , howpublished =

Reference 66

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.538794Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 81bd157d-3446-4f4c-bed0-dc027aa9cdbc · outbound

This paper cites an unresolved cited work.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Unresolved cited work

Reference 67

Resolution: unresolved; raw_fallback, observed 2026-05-13T17:13:51.540381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 15f9fe67-6c11-4ac6-ab47-fc57bdde959b · outbound

This paper cites an unresolved cited work.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Unresolved cited work

Reference 68

Resolution: parse uncertain; raw_fallback, observed 2026-05-13T17:13:51.542011Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c49db7c6-8185-4259-95d3-9fff7cd80529 · outbound

This paper cites An overview of 11 proposals for building safe advanced AI.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small An overview of 11 proposals for building safe advanced AI

Reference 69

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.461849Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 06f26e36-fbd1-47b3-aeed-72ee147eb75d · outbound

This paper cites A ttention is not E xplanation.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small A ttention is not E xplanation

Reference 70

Resolution: verified exact; doi, observed 2026-05-13T17:13:51.464099Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 878d1a18-f906-423c-ad06-2020161a1e8d · outbound

This paper cites Optimal Brain Damage , url =.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small Optimal Brain Damage , url =

Reference 71

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.543568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 26bf98f5-93e2-45b6-8e3c-209314a33acc · outbound

This paper cites 2022 , journal=.

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small 2022 , journal=

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-05-13T17:13:51.547451Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Pith citing papers

Observation bd07232b-7a32-41ac-ac35-9ab414b28ddb · inbound

Progress measures for grokking via mechanistic interpretability cites this paper.

Progress measures for grokking via mechanistic interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-05-14T21:52:56.157111Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 16867590-ebb7-473c-bb39-a4221f87c667 · inbound

Eliciting Latent Predictions from Transformers with the Tuned Lens cites this paper.

Eliciting Latent Predictions from Transformers with the Tuned Lens Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 93

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9b262013-a5bf-47ad-a29c-b8745b7cc891 · inbound

Sparse Autoencoders Find Highly Interpretable Features in Language Models cites this paper.

Sparse Autoencoders Find Highly Interpretable Features in Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-05-24T06:44:02.219327Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 06c1682f-2943-4fdf-9c88-a1c241b5c5a9 · inbound

Massive Activations in Large Language Models cites this paper.

Massive Activations in Large Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 89

Resolution: verified exact; local_arxiv, observed 2026-05-16T07:02:53.926612Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5eb24e17-4314-437f-9002-6296ee8a9797 · inbound

How to use and interpret activation patching cites this paper.

How to use and interpret activation patching Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-05-16T20:34:06.947508Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 73623492-eea4-4e80-a147-caa65323a6c5 · inbound

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 cites this paper.

Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2 Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 7

Resolution: verified exact; local_arxiv, observed 2026-05-15T05:47:20.043114Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 74c04229-41bc-4e49-a463-c0e69e89325a · inbound

METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring cites this paper.

METAGENE-1: Metagenomic Foundation Model for Pandemic Monitoring Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T22:18:23.641247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 506f5d05-097b-47e5-8de2-c7c498d0d4b7 · inbound

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words cites this paper.

Rethinking Evaluation of Sparse Autoencoders through the Representation of Polysemous Words Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-10T21:28:16.037905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb34adb7-acd4-4b6a-83e0-145a026b5f36 · inbound

Task Vectors in In-Context Learning: Emergence, Formation, and Benefit cites this paper.

Task Vectors in In-Context Learning: Emergence, Formation, and Benefit Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-10T20:15:28.427015Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation afab162a-b487-4298-9b9a-441122dd8fd5 · inbound

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition cites this paper.

Interpretability in Parameter Space: Minimizing Mechanistic Description Length with Attribution-based Parameter Decomposition Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-10T14:55:02.270268Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ac73ebc-e5f0-4645-b3e4-e0a97897b17c · inbound

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models cites this paper.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.745081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0556a0d9-92db-4033-b964-1d228dfcbde1 · inbound

Structure Development in List-Sorting Transformers cites this paper.

Structure Development in List-Sorting Transformers Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T23:32:04.152449Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6699a44f-329f-4556-90f4-bbebab7ace34 · inbound

Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability cites this paper.

Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 98

Resolution: unresolved; no resolver link, observed 2026-08-09T22:08:49.514280Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dbe5dc59-dc06-4da0-aeb6-7b7df836aba7 · inbound

Discovering Chunks in Neural Embeddings for Interpretability cites this paper.

Discovering Chunks in Neural Embeddings for Interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-09T14:29:20.143673Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5677b01-3877-4b22-961c-ac1a439d4c43 · inbound

Studying Cross-cluster Modularity in Neural Networks cites this paper.

Studying Cross-cluster Modularity in Neural Networks Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-09T12:08:22.889317Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3faaf77c-0529-4876-97a7-607826861f51 · inbound

Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging cites this paper.

Fine, I'll Merge It Myself: A Multi-Fidelity Framework for Automated Model Merging Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-08T23:51:29.437526Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ab72c83-bf32-4747-89cd-887135d947a0 · inbound

Sparse Autoencoders Do Not Find Canonical Units of Analysis cites this paper.

Sparse Autoencoders Do Not Find Canonical Units of Analysis Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-08T21:12:13.878104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d1b64ae-978c-4a90-b109-83f02abc0433 · inbound

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation cites this paper.

You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 109

Resolution: unresolved; no resolver link, observed 2026-08-08T19:15:55.076336Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7766895-4d45-4b23-ab7f-ee6e2c54a899 · inbound

A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management cites this paper.

A Frontier AI Risk Management Framework: Bridging the Gap Between Current AI Practices and Established Risk Management Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-08T14:48:44.813113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b43ceb3a-bc7d-49f0-8ed7-1d01645c071e · inbound

On Mechanistic Circuits for Extractive Question-Answering cites this paper.

On Mechanistic Circuits for Extractive Question-Answering Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-08T11:01:28.934946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation edb7054f-6d58-4845-83de-4659040a41f8 · inbound

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning cites this paper.

Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-07T22:56:40.300816Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 55c3bffa-c6e7-440d-88ef-8f86b156cbb9 · inbound

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis cites this paper.

Pierce the Mists, Greet the Sky: Decipher Knowledge Overshadowing via Knowledge Circuit Analysis Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-07T15:39:19.823946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b2fd7b59-8fd2-4e9c-9f18-1af68ddb3d58 · inbound

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models cites this paper.

Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-07T15:38:01.163498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 498a66e8-0e85-4739-925d-87adffcf6165 · inbound

Void in Language Models cites this paper.

Void in Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T15:37:03.554660Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3e2c7f5a-3e4c-447f-84e2-551669f66c45 · inbound

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence cites this paper.

Beyond Induction Heads: In-Context Meta Learning Induces Multi-Phase Circuit Emergence Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-07T15:00:58.165439Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 726d0a80-e229-4ab5-8293-e2c5e2121d26 · inbound

How Syntax Specialization Emerges in Language Models cites this paper.

How Syntax Specialization Emerges in Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T14:18:02.941819Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10673e84-3e3d-497b-91a0-9cf3f210ee49 · inbound

Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities cites this paper.

Unveiling Instruction-Specific Neurons & Experts: An Analytical Framework for LLM's Instruction-Following Capabilities Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-07T13:43:23.280878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a44dc603-4a85-406b-9742-f1b0b0604356 · inbound

Expert Survey: AI Reliability & Security Research Priorities cites this paper.

Expert Survey: AI Reliability & Security Research Priorities Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T13:31:01.134755Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e34ae475-2f13-495c-9b01-b3495503fece · inbound

Mamba Knockout for Unraveling Factual Information Flow cites this paper.

Mamba Knockout for Unraveling Factual Information Flow Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:35:19.671001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 25085deb-1076-4066-a0b5-1f3681d0afe1 · inbound

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race cites this paper.

Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of Race Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-07T12:13:19.352932Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 795ad8e5-0f9c-470e-b00f-ec2eff7fd9fe · inbound

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective cites this paper.

Dissecting Bias in LLMs: A Mechanistic Interpretability Perspective Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T10:29:44.987123Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2b18c6f-035b-4e61-bfb7-531a1aa1829f · inbound

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models cites this paper.

InverseScope: Scalable Activation Inversion for Interpreting Large Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T05:44:34.868186Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f79164a6-a64d-4590-95be-a8493a301f24 · inbound

Extrapolation by Association: Length Generalization Transfer in Transformers cites this paper.

Extrapolation by Association: Length Generalization Transfer in Transformers Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T04:59:23.693310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 39793d58-ccfa-490b-b150-96a62e62d4c3 · inbound

Stochastic Parameter Decomposition cites this paper.

Stochastic Parameter Decomposition Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T22:48:39.358150Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85216b34-3275-4f8e-8904-190d27a6f832 · inbound

How Do Vision-Language Models Process Conflicting Information Across Modalities? cites this paper.

How Do Vision-Language Models Process Conflicting Information Across Modalities? Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T20:47:07.394735Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a1e61622-ebda-4274-882d-000351d125d4 · inbound

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability cites this paper.

Transformers Don't Need LayerNorm at Inference Time: Scaling LayerNorm Removal to GPT-2 XL and the Implications for Mechanistic Interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T20:31:17.798498Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92c1d813-3288-4c50-858a-a1b32c741045 · inbound

Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models cites this paper.

Loki's Dance of Illusions: A Comprehensive Survey of Hallucination in Large Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 111

Resolution: unresolved; no resolver link, observed 2026-08-07T10:18:59.242409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b4444bd-35fc-4680-8718-f0de87b4c9c1 · inbound

A Survey on Latent Reasoning cites this paper.

A Survey on Latent Reasoning Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 108

Resolution: unresolved; no resolver link, observed 2026-08-06T19:14:31.787447Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82a0b61e-b35f-4d95-a5da-5a758d3c941d · inbound

Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers cites this paper.

Adversarial Activation Patching: A Framework for Detecting and Mitigating Emergent Deception in Safety-Aligned Transformers Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-06T18:00:51.725380Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3a97b7dc-8cdf-41a1-9c7d-070759ea9c63 · inbound

Algorithm Development in Neural Networks: Insights from the Streaming Parity Task cites this paper.

Algorithm Development in Neural Networks: Insights from the Streaming Parity Task Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 14

Resolution: malformed identifier; no resolver link, observed 2026-08-06T17:51:44.752240Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d1d4c40-723c-48b0-92a5-ca7436e0cd66 · inbound

Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them cites this paper.

Scalpel vs. Hammer: GRPO Amplifies Existing Capabilities, SFT Replaces Them Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T17:52:01.676363Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2201a38b-4fcd-4c41-8296-90544649bed1 · inbound

Scaling laws for activation steering with Llama 2 models and refusal mechanisms cites this paper.

Scaling laws for activation steering with Llama 2 models and refusal mechanisms Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T17:05:04.509549Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 51295c71-28af-4e5a-b7f4-85e9fa1a7d44 · inbound

LLMs Encode Harmfulness and Refusal Separately cites this paper.

LLMs Encode Harmfulness and Refusal Separately Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T17:03:16.793689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f76758b2-cf9a-4c8c-8444-5c3b49d110d9 · inbound

Insights into a radiology-specialised multimodal large language model with sparse autoencoders cites this paper.

Insights into a radiology-specialised multimodal large language model with sparse autoencoders Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T16:40:44.385051Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64e739de-8800-4a24-926d-73ab73659a3f · inbound

On the transferability of Sparse Autoencoders for interpreting compressed models cites this paper.

On the transferability of Sparse Autoencoders for interpreting compressed models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T15:24:45.806155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 500d88f3-9155-479b-b9c1-1b0dec2ce635 · inbound

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations cites this paper.

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T05:30:19.195128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c86245e-2728-4fdc-affe-b2b977a3905b · inbound

NEAT: Concept driven Neuron Attribution in LLMs cites this paper.

NEAT: Concept driven Neuron Attribution in LLMs Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-05T18:01:19.714746Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd91d2a0-b672-47c7-bdc3-51f66fabe751 · inbound

From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits cites this paper.

From Indirect Object Identification to Syllogisms: Exploring Binary Mechanisms in Transformer Circuits Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T17:37:53.695806Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 019fb5de-08b8-4526-ab5f-2d97bed4325b · inbound

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation cites this paper.

HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-05T17:16:33.076002Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dac7148a-b2ec-45d9-a02f-1e1b7f3be1e3 · inbound

All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens cites this paper.

All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T18:50:56.711463Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 78f72428-eba0-4732-a9e6-1ca4723e0d93 · inbound

Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal cites this paper.

Beyond I'm Sorry, I Can't: Dissecting Large Language Model Refusal Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 35

Resolution: verified exact; local_arxiv, observed 2026-05-18T18:56:45.794536Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4b27728d-2133-4603-9263-342399895f24 · inbound

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content cites this paper.

Towards Inclusive Toxic Content Moderation: Addressing Vulnerabilities to Adversarial Attacks in Toxicity Classifiers Tackling LLM-generated Content Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T16:40:31.230569Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b19b3df4-f598-416f-ac83-e9462e2f911c · inbound

From Features to Actions: Explainability in Traditional and Agentic AI Systems cites this paper.

From Features to Actions: Explainability in Traditional and Agentic AI Systems Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-03T03:50:17.552737Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26f2a1fc-a6e3-4916-ab4e-87dbfafc3d56 · inbound

Prototype Transformer: Towards Language Model Architectures Interpretable by Design cites this paper.

Prototype Transformer: Towards Language Model Architectures Interpretable by Design Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-03T00:02:45.942638Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e26656e-1c79-49ac-b8b8-7fb793272cb3 · inbound

Transformers converge to invariant algorithmic cores cites this paper.

Transformers converge to invariant algorithmic cores Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-02T20:46:32.835730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb22fcdc-9130-478d-995c-dfdbbe5d6e62 · inbound

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs cites this paper.

Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-02T16:59:55.496930Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44187884-afe5-412c-a825-b27170415412 · inbound

PhiNet: Speaker Verification with Phonetic Interpretability cites this paper.

PhiNet: Speaker Verification with Phonetic Interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 57

Resolution: verified exact; local_arxiv, observed 2026-05-13T21:13:16.407720Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 5b7272f9-483c-48c7-88b3-15cefa33a3f9 · inbound

Speaking of Language: Reflections on Metalanguage Research in NLP cites this paper.

Speaking of Language: Reflections on Metalanguage Research in NLP Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 8

Resolution: metadata mismatch; local_arxiv, observed 2026-05-13T20:28:14.115088Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 1ca5196b-4a7d-425b-9f27-2468f91b1fea · inbound

CURE:Circuit-Aware Unlearning for LLM-based Recommendation cites this paper.

CURE:Circuit-Aware Unlearning for LLM-based Recommendation Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 34

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 10d8aaa4-b06a-482a-bec8-22e97b4d6c68 · inbound

A Numerical PDEs Approach to Evolution Equations in Shape Analysis Based on Regularized Morphoelasticity cites this paper.

A Numerical PDEs Approach to Evolution Equations in Shape Analysis Based on Regularized Morphoelasticity Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-13T12:04:13.336341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8a2fadcb-f376-4d46-8e0b-9b5e98569108 · inbound

Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings cites this paper.

Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 71

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 24aed8c1-dc66-43b6-acd5-c4ed346fcbca · inbound

Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs cites this paper.

Hessian-Enhanced Token Attribution (HETA): Interpreting Autoregressive LLMs Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 41

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0c9a623c-fb56-483c-b557-82967e02c085 · inbound

The Illusion of Equivalence: Systematic FP16 Divergence in KV-Cached Autoregressive Inference cites this paper.

The Illusion of Equivalence: Systematic FP16 Divergence in KV-Cached Autoregressive Inference Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 22

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9da0b9f1-91f3-469b-8bc6-b7a1b140cd55 · inbound

Grokking of Diffusion Models: Case Study on Modular Addition cites this paper.

Grokking of Diffusion Models: Case Study on Modular Addition Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 95491ea6-98c9-4d5e-b15a-dcaccddc61d3 · inbound

Cell-Based Representation of Relational Binding in Language Models cites this paper.

Cell-Based Representation of Relational Binding in Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 33

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f4f6c0fb-a348-48aa-aebc-3816b7489f5a · inbound

Graph Memory Transformer (GMT) cites this paper.

Graph Memory Transformer (GMT) Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 37

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0ade4e87-c831-40a6-b1c2-565b4b6acb68 · inbound

Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs cites this paper.

Perturbation Probing: A Two-Pass-per-Prompt Diagnostic for FFN Behavioral Circuits in Aligned LLMs Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 295211e9-5eef-4df4-9d7e-4673d45abf88 · inbound

Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B cites this paper.

Borrowed Geometry: Cross-Distribution Head-Importance Fingerprints of Frozen Pretrained Gemma 4 31B Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 11

Resolution: metadata mismatch; local_arxiv, observed 2026-05-21T00:29:17.274052Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation f1e482b1-5b50-4bb2-a4d2-320534f6f623 · inbound

When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models cites this paper.

When LLMs Stop Following Steps: A Diagnostic Study of Procedural Execution in Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 6

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e32a04dc-ddcd-4fd8-a4c8-97ea88e54705 · inbound

High-Dimensional Statistics: Reflections on Progress and Open Problems cites this paper.

High-Dimensional Statistics: Reflections on Progress and Open Problems Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 104

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c6febe8e-9fbb-410c-96b4-25db81a0247d · inbound

High-Dimensional Statistics: Reflections on Progress and Open Problems cites this paper.

High-Dimensional Statistics: Reflections on Progress and Open Problems Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 104

Resolution: verified exact; local_arxiv, observed 2026-07-01T13:15:45.970687Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 8d9d24ba-9a3f-4b3e-99f6-c11c8e7502dc · inbound

Negative Before Positive: Asymmetric Valence Processing in Large Language Models cites this paper.

Negative Before Positive: Asymmetric Valence Processing in Large Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 60d326e6-7a38-4a6a-87a5-ab761f42f2bf · inbound

The Position Curse: LLMs Struggle to Locate the Last Few Items in a List cites this paper.

The Position Curse: LLMs Struggle to Locate the Last Few Items in a List Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 24

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9bac8d96-335f-4482-96c3-bb725c4417a6 · inbound

Hallucination Detection via Activations of Open-Weight Proxy Analyzers cites this paper.

Hallucination Detection via Activations of Open-Weight Proxy Analyzers Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 624c863e-9194-4106-b8a0-391d003b3199 · inbound

Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions cites this paper.

Where's the Plan? Locating Latent Planning in Language Models with Lightweight Mechanistic Interventions Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 23

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 06313e4a-423a-41a2-b486-a89aa6c50ec0 · inbound

Tool Calling is Linearly Readable and Steerable in Language Models cites this paper.

Tool Calling is Linearly Readable and Steerable in Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 74

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation b8a59202-11fd-4fe6-8ee4-3e64790d516c · inbound

Architecture, Not Scale: Circuit Localization in Large Language Models cites this paper.

Architecture, Not Scale: Circuit Localization in Large Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 70994fb7-94ea-4d5d-96c8-85c819f99643 · inbound

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations cites this paper.

The Geometry of Forgetting: Temporal Knowledge Drift as an Independent Axis in LLM Representations Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 38

Resolution: malformed identifier; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2e2b1232-1b81-4600-84a8-3288a850731b · inbound

Dissecting Jet-Tagger Through Mechanistic Interpretability cites this paper.

Dissecting Jet-Tagger Through Mechanistic Interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 16

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation e30a75e0-8f51-4920-8f12-ef35c4eeb491 · inbound

Learning Less Is More: Premature Upper-Layer Attention Specialization Hurts Language Model Pretraining cites this paper.

Learning Less Is More: Premature Upper-Layer Attention Specialization Hurts Language Model Pretraining Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 17

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6701c411-84e5-4ab4-b5f3-a6b8f4729de6 · inbound

Not How Many, But Which: Parameter Placement in Low-Rank Adaptation cites this paper.

Not How Many, But Which: Parameter Placement in Low-Rank Adaptation Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 87

Resolution: verified exact; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation ba5cb654-c967-4782-a1b5-f4f2a2ad089c · inbound

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender cites this paper.

GKnow: Measuring the Entanglement of Gender Bias and Factual Gender Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 28

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T17:13:51.588363Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 144bb3e7-cbed-4722-99e3-b7f307725fff · inbound

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces cites this paper.

Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 82

Resolution: verified exact; local_arxiv, observed 2026-05-14T20:17:55.505913Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation df8da93c-ed81-44b9-bbf3-ef552741e46c · inbound

How to Interpret Agent Behavior cites this paper.

How to Interpret Agent Behavior Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-05-14T18:27:35.915812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation a254d540-c15f-4cb6-bff0-884c2fcae2d8 · inbound

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands cites this paper.

Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 68

Resolution: metadata mismatch; local_arxiv, observed 2026-06-30T20:55:03.906712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 7a215416-a70c-4cab-a9be-a0aead2162ef · inbound

Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE cites this paper.

Beyond Linear Superposition: Discovering Climate Features in AI Weather Models with KAN-SAE Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-20T14:48:23.205344Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fad22ae8-4744-45ba-a445-697e11bd43c6 · inbound

Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination cites this paper.

Causal Evidence for Attention Head Imbalance in Modality Conflict Hallucination Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-05-20T06:28:05.509681Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation d0b69103-8ec1-4b6f-a902-5c481152ec00 · inbound

Manifold-Guided Attention Steering cites this paper.

Manifold-Guided Attention Steering Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 20

Resolution: verified exact; local_arxiv, observed 2026-05-22T09:14:45.333190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 4ecd92ed-d6ef-4ffd-8726-637478f30ca8 · inbound

From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models cites this paper.

From Correlation to Cause: A Five-Stage Methodology for Feature Analysis in Transformer Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-22T07:01:11.963153Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation c25b2f2a-f7fb-4b4f-a9eb-49ae70c531fa · inbound

Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability cites this paper.

Transformer Field Theory: A Response-Theoretic Approach to Mechanistic Interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 4

Resolution: verified exact; local_arxiv, observed 2026-06-30T12:04:38.219967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 318a0fc9-99c2-44c0-a366-d59510d6a87f · inbound

Binding Visual Features Point by Point cites this paper.

Binding Visual Features Point by Point Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-06-29T23:44:03.323191Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fabec0ee-ae7b-4e8e-a546-cf076f665328 · inbound

Tracing Computation Density in LLMs cites this paper.

Tracing Computation Density in LLMs Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 3

Resolution: metadata mismatch; local_arxiv, observed 2026-06-29T18:23:50.638460Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 6f718af9-9b38-4c18-a23d-36789c7c6ed3 · inbound

Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection cites this paper.

Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-06-29T07:13:16.594466Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 9d4c1b38-3e18-4c41-9c1e-be69f6bb65e6 · inbound

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning cites this paper.

Mechanistic Diagnostics of Spatial Lexical Bias in Multimodal Large Language Model Spatial Reasoning Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 50

Resolution: verified exact; local_arxiv, observed 2026-07-01T23:16:24.594953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 63e274be-e5d8-4e06-b022-a065b5ec8a76 · inbound

A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting cites this paper.

A Negative Result on Cross-Model Activation Transfer in a Pythia Multi-Hop Setting Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 17

Resolution: verified exact; local_arxiv, observed 2026-07-02T03:36:29.800981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 2c07424f-6a92-4b99-a595-ceb5bbfca97d · inbound

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs cites this paper.

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 34

Resolution: verified exact; local_arxiv, observed 2026-07-02T02:16:26.475224Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0bb5532a-d2b0-472f-aaa0-dfc50bd77957 · inbound

STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations cites this paper.

STRIDE: Training Data Attribution via Sparse Recovery from Subset Perturbations Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 88

Resolution: verified exact; local_arxiv, observed 2026-07-02T06:06:41.392147Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 367da854-a7ea-46fe-a2d0-b520df8d094b · inbound

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models cites this paper.

Pattern Selectivity is Not Task-Causal Structure: A Cross-Architecture Mechanistic Study of Composed-Task Circuits in 1B-Class Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 2

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T07:06:44.456142Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation 0390f0d2-67fb-423e-ac7e-3417df484cc7 · inbound

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability cites this paper.

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-06-28T02:11:29.080954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.

Observation fe30d291-3b8f-4a69-8570-afdda8478029 · inbound

Sparsely gated tiny linear experts cites this paper.

Sparsely gated tiny linear experts Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 33

Resolution: metadata mismatch; local_arxiv, observed 2026-07-02T16:17:09.306780Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.