Paper Citation Record · LEDGER

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition

As of 23 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2601.12879.

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

pith.paper-citation-record.v1
2601.12879 v2

Coverage vector

measured 35 of 35 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-03T09:43:52.365784Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-23T06:30:58.430688+00:00

measured 0 of 0 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links

measured 0 of 1 external citation measurements

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

Source: cited_works

Reference resolution

35 of 35 outbound references displayed

verified exact0
verified fuzzy0
unresolved35
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d0cc2fb5-b57f-4b0a-81a7-667964faf50b · outbound

This paper cites On the biology of a large language model,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition On the biology of a large language model,

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.125275Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 391cb797-e7a6-493c-be4d-39c5b88a5fe3 · outbound

This paper cites Neuron-level circuits: Pruning MLPs to interpret their weights,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Neuron-level circuits: Pruning MLPs to interpret their weights,

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.235460Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7548e98-44fb-43b2-a42c-a944b2ad7626 · outbound

This paper cites Towards monosemanticity: Decomposing language models with dictionary learning,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Towards monosemanticity: Decomposing language models with dictionary learning,

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.304775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 802fd163-2658-46b5-8e27-14945fd23d91 · outbound

This paper cites Towards automated circuit discovery for mechanistic interpretability,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Towards automated circuit discovery for mechanistic interpretability,

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.398597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faa2c21d-e8bc-478d-858e-625c118b0fa3 · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Sparse autoencoders find highly interpretable features in language models,

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.534573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd28ad7c-102e-440f-a88c-684c6b7f23d3 · outbound

This paper cites A mathematical framework for transformer circuits,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition A mathematical framework for transformer circuits,

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.641496Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 835c8bab-0aa1-4283-ace1-20176783805a · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Scaling and evaluating sparse autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.711493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f7923efe-a802-45c1-8707-cda8d1dfea50 · outbound

This paper cites Weight-sparse transformers enable circuit- level interpretability,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Weight-sparse transformers enable circuit- level interpretability,

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.812527Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31ae78bf-96ed-4ae4-9325-64323a8dc453 · outbound

This paper cites How does GPT-2 compute greater- than? Interpreting mathematical abilities in a pre-trained language model,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition How does GPT-2 compute greater- than? Interpreting mathematical abilities in a pre-trained language model,

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:49.923000Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab53a23b-8503-44ad-9294-6d414d599586 · outbound

This paper cites Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.035165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b0637bd-db8f-4c28-beb2-1e266751d905 · outbound

This paper cites Locating and editing factual associations in GPT,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Locating and editing factual associations in GPT,

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.137289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcc84977-3b77-42ba-8fc9-d8c2854ad4db · outbound

This paper cites Opening the AI black box: program synthesis via mechanistic interpretability.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Opening the AI black box: program synthesis via mechanistic interpretability

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.257577Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6266d2e6-4d8b-4f1a-a207-59b4d869d5d4 · outbound

This paper cites Progress measures for grokking via mechanistic interpretability,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Progress measures for grokking via mechanistic interpretability,

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.367945Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06044f44-1c1d-493f-8975-e7a5cd4fb4df · outbound

This paper cites Zoom in: An introduction to circuits,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Zoom in: An introduction to circuits,

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.503592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4abdb7b7-c840-403d-b933-8e9640cbb065 · outbound

This paper cites In-context learning and induction heads,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition In-context learning and induction heads,

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.599223Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c0de4904-b85e-414f-b009-f53bfdfae9a4 · outbound

This paper cites Interpretability in weight-sparse language models,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Interpretability in weight-sparse language models,

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.694901Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3c5c2b99-3f9d-4601-8375-34f7b0095473 · outbound

This paper cites WinoGrande: An adversarial Winograd schema challenge at scale,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition WinoGrande: An adversarial Winograd schema challenge at scale,

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.793355Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a87aa4f-61bd-4a52-bd04-0984d6918f92 · outbound

This paper cites Axiomatic attribution for deep networks,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Axiomatic attribution for deep networks,

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.857300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77943da8-d398-4488-a65e-a657a04e3cff · outbound

This paper cites Graph attention networks,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Graph attention networks,

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:50.918324Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bb9c5879-4246-498a-9555-3f30ae24c950 · outbound

This paper cites A tutorial on spectral clustering,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition A tutorial on spectral clustering,

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.014469Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3db8098d-c348-4ddc-ba18-173046f9eed1 · outbound

This paper cites Interpretability in the wild: A circuit for indirect object identification in GPT-2 small,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Interpretability in the wild: A circuit for indirect object identification in GPT-2 small,

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.120300Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3309cf29-2ca0-489c-a845-785cf7340b0f · outbound

This paper cites HellaSwag: Can a machine really finish your sentence?.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition HellaSwag: Can a machine really finish your sentence?

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.223515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1ab5c987-1b91-4bbf-a132-c016e5f8b48b · outbound

This paper cites Defining and quantifying the emergence of sparse concepts in DNNs,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Defining and quantifying the emergence of sparse concepts in DNNs,

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.305333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 14567aa2-d0be-4117-9d97-a26f66e3f28e · outbound

This paper cites Explaining Generalization Power of a DNN Using Interactive Concepts.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Explaining Generalization Power of a DNN Using Interactive Concepts

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.389495Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 108f8857-6bb4-4ef9-a159-34eaad577db0 · outbound

This paper cites Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.444060Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7661e431-78d3-4658-89f7-ff4c76786339 · outbound

This paper cites Discovering transformer circuits via a hybrid attribution and pruning framework,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Discovering transformer circuits via a hybrid attribution and pruning framework,

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.571509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 32c0e022-4ff3-4b37-ab01-bc282130c0b7 · outbound

This paper cites Finding Transformer Circuits with Edge Pruning.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Finding Transformer Circuits with Edge Pruning

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.664374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 41f662ed-8cda-45f9-8513-d84adc21fdd9 · outbound

This paper cites The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.759455Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e6ba8fc2-78e3-4460-b558-56d18494edc5 · outbound

This paper cites Functional faithfulness in the wild: Circuit discovery with differentiable computation graph pruning,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Functional faithfulness in the wild: Circuit discovery with differentiable computation graph pruning,

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.848811Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5654fa34-3495-42a0-9255-8f73d36c51b5 · outbound

This paper cites Automatically Identifying Local and Global Circuits with Linear Computation Graphs.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Automatically Identifying Local and Global Circuits with Linear Computation Graphs

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:51.976205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 869198f6-eea5-4563-9323-7ec30859625e · outbound

This paper cites Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:52.064760Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0d05f45f-e122-4ca0-b692-394ffce71a70 · outbound

This paper cites Weight-sparse transformers have interpretable circuits,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Weight-sparse transformers have interpretable circuits,

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:52.156854Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 320a465d-0560-4a4a-8d81-b6836593b1a3 · outbound

This paper cites Language models can explain neurons in language models,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Language models can explain neurons in language models,

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:52.248658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3f8a902-d44a-4d03-aac9-0cbb97c3e0c1 · outbound

This paper cites Scaling monosemanticity: Extracting interpretable features from Claude 3 Sonnet,.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Scaling monosemanticity: Extracting interpretable features from Claude 3 Sonnet,

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:52.314120Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 099071a3-e247-46cf-b4f2-f173e10818af · outbound

This paper cites Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla.

Hierarchical Sparse Circuit Extraction from Billion-Parameter Language Models through Scalable Attribution Graph Decomposition Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-03T09:43:52.365784Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.