Paper Citation Record · LEDGER

GPT-2 Through the Lens of Vector Symbolic Architectures

As of 23 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2412.07947.

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

pith.paper-citation-record.v1
2412.07947 v1

Coverage vector

measured 30 of 30 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-11T18:26:31.877198Z

measured 30 of 30 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

30 of 30 outbound references displayed

verified exact2
verified fuzzy16
unresolved11
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 7758e4f3-3a28-42c5-b8a1-7070c99d6242 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

GPT-2 Through the Lens of Vector Symbolic Architectures Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.787953Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 796bb306-8b4e-4317-842e-e1b24d79e8c5 · outbound

This paper cites Refusal in Language Models Is Mediated by a Single Direction.

GPT-2 Through the Lens of Vector Symbolic Architectures Refusal in Language Models Is Mediated by a Single Direction

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.729269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 08e8681f-b9e7-47c1-9b12-504b2fb065ae · outbound

This paper cites Understanding the role of individual units in a deep neural network.

GPT-2 Through the Lens of Vector Symbolic Architectures Understanding the role of individual units in a deep neural network

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.735596Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ee7882b-f308-4358-a67e-a51d6859b137 · outbound

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

GPT-2 Through the Lens of Vector Symbolic Architectures Towards monosemanticity: Decomposing language models with dictionary learning

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.771967Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation d076f25f-5b75-4746-8605-5a594b4c0858 · outbound

This paper cites What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models.

GPT-2 Through the Lens of Vector Symbolic Architectures What Is One Grain of Sand in the Desert? Analyzing Individual Neurons in Deep NLP Models

Reference 5

Resolution: verified exact; local_arxiv, observed 2026-08-11T18:26:32.044336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation fca53ecb-cc4b-41ae-8b21-ba658ecb99c0 · outbound

This paper cites The Faiss library.

GPT-2 Through the Lens of Vector Symbolic Architectures The Faiss library

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.752031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6427963-27b0-4806-ab62-799a86ec6dd1 · outbound

This paper cites Analyzing Individual Neurons in Pre-trained Language Models.

GPT-2 Through the Lens of Vector Symbolic Architectures Analyzing Individual Neurons in Pre-trained Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.758618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 338cba8a-e0ea-4678-8ac1-748256e616d6 · outbound

This paper cites A mathematical framework for transformer circuits.

GPT-2 Through the Lens of Vector Symbolic Architectures A mathematical framework for transformer circuits

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.756932Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 26770b68-c2b7-4baf-9174-316f7528eb9b · outbound

This paper cites Toy Models of Superposition.

GPT-2 Through the Lens of Vector Symbolic Architectures Toy Models of Superposition

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.769074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c6c496f7-5c29-4497-b0ad-e1c114b92182 · outbound

This paper cites Not All Language Model Features Are One-Dimensionally Linear.

GPT-2 Through the Lens of Vector Symbolic Architectures Not All Language Model Features Are One-Dimensionally Linear

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.774536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f2f4a2c-5c7d-4d50-87fb-3a6a42c69765 · outbound

This paper cites Representing objects, relations, and sequences.

GPT-2 Through the Lens of Vector Symbolic Architectures Representing objects, relations, and sequences

Reference 11

Resolution: verified exact; doi, observed 2026-08-11T18:26:31.988748Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a1ced7f3-3595-45ef-a0da-162188957faa · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

GPT-2 Through the Lens of Vector Symbolic Architectures Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.785201Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e1ab188c-1210-43a9-8620-013c5414aa2b · outbound

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

GPT-2 Through the Lens of Vector Symbolic Architectures How does GPT-2 compute greater-than?: Inter- preting mathematical abilities in a pre-trained language model

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.740205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c07703d1-d312-4fbc-b639-32a5b57526b7 · outbound

This paper cites Linearity of relation decoding in transformer language models.

GPT-2 Through the Lens of Vector Symbolic Architectures Linearity of relation decoding in transformer language models

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.724057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation e6e64430-2838-47fc-ba87-15c9cad5e039 · outbound

This paper cites On the origins of linear representations in large language models.

GPT-2 Through the Lens of Vector Symbolic Architectures On the origins of linear representations in large language models

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.708249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 13fb2313-78f3-4fb8-b5db-86063bdfb070 · outbound

This paper cites Vector Symbolic Architectures as a Computing Framework for Emerging Hardware.

GPT-2 Through the Lens of Vector Symbolic Architectures Vector Symbolic Architectures as a Computing Framework for Emerging Hardware

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.805639Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc1fb277-2cf7-4e89-aefe-5111059f357d · outbound

This paper cites Emergent world representations: Exploring a sequence model trained on a synthetic task.

GPT-2 Through the Lens of Vector Symbolic Architectures Emergent world representations: Exploring a sequence model trained on a synthetic task

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.688777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation a6db98ca-0036-473c-a293-fa5c71d3aca4 · outbound

This paper cites The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets.

GPT-2 Through the Lens of Vector Symbolic Architectures The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.815663Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23c1a93c-aa5e-4dc9-b0a2-797330c62b8d · outbound

This paper cites Distributed representations of words and phrases and their compositionality.

GPT-2 Through the Lens of Vector Symbolic Architectures Distributed representations of words and phrases and their compositionality

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.667556Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ea9229a6-150b-4ee2-bc26-6091467baaa9 · outbound

This paper cites Vector-based models of semantic composition.

GPT-2 Through the Lens of Vector Symbolic Architectures Vector-based models of semantic composition

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.635568Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ed079425-7613-466a-a5b3-7e43a1cf1b29 · outbound

This paper cites TransformerLens.

GPT-2 Through the Lens of Vector Symbolic Architectures TransformerLens

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.565779Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation bbcdc945-31ae-4975-a3b8-47baf71456db · outbound

This paper cites Zoom in: An introduction to circuits.

GPT-2 Through the Lens of Vector Symbolic Architectures Zoom in: An introduction to circuits

Reference 22

Resolution: malformed identifier; no resolver link, observed 2026-08-11T18:26:31.836832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 345cbf79-b6a4-47ae-bb4f-5cf7c5c888e8 · outbound

This paper cites The Linear Representation Hypothesis and the Geometry of Large Language Models.

GPT-2 Through the Lens of Vector Symbolic Architectures The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.841941Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e03c6f-f732-4ce4-9258-f9d3d15b55c8 · outbound

This paper cites Language models are unsupervised multitask learners.

GPT-2 Through the Lens of Vector Symbolic Architectures Language models are unsupervised multitask learners

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.545844Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation ef138b35-7a94-4708-8934-ebd9297c0f6f · outbound

This paper cites BERT rediscovers the classical NLP pipeline.

GPT-2 Through the Lens of Vector Symbolic Architectures BERT rediscovers the classical NLP pipeline

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.522049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation c77ff91e-2881-4ad7-9768-2ba2206d2b8a · outbound

This paper cites What do you learn from context? Probing for sentence structure in contextualized word representations.

GPT-2 Through the Lens of Vector Symbolic Architectures What do you learn from context? Probing for sentence structure in contextualized word representations

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.498802Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 7d2583b1-4ac4-4877-8845-bd680415ec82 · outbound

This paper cites Toward A Mathematical Framework for Computation in Superposition.

GPT-2 Through the Lens of Vector Symbolic Architectures Toward A Mathematical Framework for Computation in Superposition

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.398218Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 76013719-562f-44e7-8a19-538648f0a9d4 · outbound

This paper cites Attention is all you need.

GPT-2 Through the Lens of Vector Symbolic Architectures Attention is all you need

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.330795Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 33a2a9a5-0403-49ca-8931-48ee3297f901 · outbound

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

GPT-2 Through the Lens of Vector Symbolic Architectures Interpretability in the wild: a circuit for indirect object identification in GPT-2 small

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-11T18:26:32.311829Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.

Observation 95a65c0b-bca0-44ed-9ad8-155958a7f865 · outbound

This paper cites Relational Composition in Neural Networks: A Survey and Call to Action.

GPT-2 Through the Lens of Vector Symbolic Architectures Relational Composition in Neural Networks: A Survey and Call to Action

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-11T18:26:31.877198Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.