Paper Citation Record · LEDGER

Partially Rewriting a Transformer in Natural Language

As of 22 August 2026, this Paper Citation Record lists 16 of 16 outbound references and 1 inbound Pith citation observation for arXiv:2501.18838.

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

pith.paper-citation-record.v1
2501.18838 v1

Coverage vector

measured 16 of 16 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T22:21:50.772580Z

measured 17 of 17 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-22T06:32:14.747728+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T18:24:51.592477Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T18:24:52.807833Z

Reference resolution

16 of 16 outbound references displayed

verified exact0
verified fuzzy5
unresolved11
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation a2548c9d-6be2-4f01-bd48-e352016201a4 · outbound

This paper cites These features of text are normally identified by looking for specific words or patterns in the text.

Partially Rewriting a Transformer in Natural Language These features of text are normally identified by looking for specific words or patterns in the text

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:21:50.968660Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 91591067-2887-4272-a171-4b85681a776c · outbound

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

Partially Rewriting a Transformer in Natural Language Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.710486Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9a54fc1-1a84-4f97-9256-7d6236cf34bd · outbound

This paper cites The Llama 3 Herd of Models.

Partially Rewriting a Transformer in Natural Language The Llama 3 Herd of Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.715615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c54b8e2-49f3-4f5c-9efb-e323be1ca9b7 · outbound

This paper cites Toy Models of Superposition.

Partially Rewriting a Transformer in Natural Language Toy Models of Superposition

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.726157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5c460729-67a8-44af-81bd-a454120eb6fd · outbound

This paper cites DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning.

Partially Rewriting a Transformer in Natural Language DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.740887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e29f0d38-d4eb-46d8-8247-0b1de984f8e0 · outbound

This paper cites Universal Neurons in GPT2 Language Models.

Partially Rewriting a Transformer in Natural Language Universal Neurons in GPT2 Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.749829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d1a4bfb8-1bce-41ae-bf01-96cc4d3259b4 · outbound

This paper cites Automatically Interpreting Millions of Features in Large Language Models.

Partially Rewriting a Transformer in Natural Language Automatically Interpreting Millions of Features in Large Language Models

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.763556Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7782f6fa-7198-4724-8b39-f66de26f4f0b · outbound

This paper cites male pronouns.

Partially Rewriting a Transformer in Natural Language male pronouns

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:21:50.983249Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 39e0b3c2-5232-4465-a5d9-d8ae4dcb571e · outbound

This paper cites Adam: A Method for Stochastic Optimization.

Partially Rewriting a Transformer in Natural Language Adam: A Method for Stochastic Optimization

Reference 1996

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.759001Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e13bc5a8-b506-4cad-8335-bc2648698899 · outbound

This paper cites com/posts/X2i9dQQK3gETCyqh2/ chris-olah-s-views-on-agi-safety.

Partially Rewriting a Transformer in Natural Language com/posts/X2i9dQQK3gETCyqh2/ chris-olah-s-views-on-agi-safety

Reference 2019

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:21:50.997845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2719546e-cf9a-4b54-a5a6-126776e3e0ba · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Partially Rewriting a Transformer in Natural Language Scaling and evaluating sparse autoencoders

Reference 2020

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.735732Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d815c96a-0612-4a4d-b531-2cc60557d7b1 · outbound

This paper cites com/posts/JKj5Krff5oKMb8TjT/ imitative-generalisation-aka-learning-the-prior-1.

Partially Rewriting a Transformer in Natural Language com/posts/JKj5Krff5oKMb8TjT/ imitative-generalisation-aka-learning-the-prior-1

Reference 2021

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:21:51.027252Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 767ca27f-dd18-4aa0-97ed-f1df005221fc · outbound

This paper cites The Pile: An 800GB Dataset of Diverse Text for Language Modeling.

Partially Rewriting a Transformer in Natural Language The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.731057Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6404486c-a83e-45fd-82a0-4d93a343ce29 · outbound

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

Partially Rewriting a Transformer in Natural Language Language models can explain neurons in language models

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T22:21:51.012245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation bd32d894-72f3-43de-a43d-bd0ce0c9275c · outbound

This paper cites Transcoders Find Interpretable LLM Feature Circuits.

Partially Rewriting a Transformer in Natural Language Transcoders Find Interpretable LLM Feature Circuits

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.720744Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e35e1049-ac4d-4c1a-8430-9702ebe0ec5b · outbound

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

Partially Rewriting a Transformer in Natural Language Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-09T22:21:50.745427Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 8ed14f3c-06e1-4796-bc8f-70f81dda4c00 · inbound

Evaluating SAE interpretability without explanations cites this paper.

Evaluating SAE interpretability without explanations Partially Rewriting a Transformer in Natural Language

Reference 19

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:24:52.843511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.