Paper Citation Record · LEDGER

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

As of 9 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 3 inbound Pith citation observations for arXiv:2502.03032.

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

pith.paper-citation-record.v1
2502.03032 v3

Coverage vector

measured 32 of 32 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-09T10:11:51.810083Z

measured 35 of 35 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-09T06:31:02.800959+00:00

measured 3 of 3 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:35:06.626592Z

measured 1 of 1 external citation measurements

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

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

Reference resolution

32 of 32 outbound references displayed

verified exact2
verified fuzzy10
unresolved20
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

0
arxiv_reference, observed 2026-08-05T02:28:24.338817Z

Outbound references

Observation 1b5f570f-fced-4b51-a3a2-55745b003cab · outbound

This paper cites Mechanistic permutability: Match features across layers.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Mechanistic permutability: Match features across layers

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.471703Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 8e2a38cf-1e5b-420a-9920-32591196071b · outbound

This paper cites Evolution of SAE Features Across Layers in LLMs.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Evolution of SAE Features Across Layers in LLMs

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.443311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02e1601b-20f5-4212-9477-e64947195964 · outbound

This paper cites E., Hume, T., Carter, S., Henighan, T., and Olah, C.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models E., Hume, T., Carter, S., Henighan, T., and Olah, C

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.447543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d55c472-3b55-4205-a041-12f6c98efdfd · outbound

This paper cites BatchTopK Sparse Autoencoders.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models BatchTopK Sparse Autoencoders

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.452310Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e0726db-180b-438b-a167-df0d0d9fc048 · outbound

This paper cites Improving Steering Vectors by Targeting Sparse Autoencoder Features.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Improving Steering Vectors by Targeting Sparse Autoencoder Features

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.456407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 04efe5ec-a6ff-4f72-bb0d-ed8023baf3e8 · outbound

This paper cites N., Lynch, A., Heimersheim, S., and Garriga-Alonso, A.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models N., Lynch, A., Heimersheim, S., and Garriga-Alonso, A

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.455008Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation f1fd3a9a-740a-4107-af88-2d7bb61ce693 · outbound

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

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.465409Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b7aadacf-6725-4519-b232-02aba34b30f3 · outbound

This paper cites Transcoders Find Interpretable LLM Feature Circuits.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Transcoders Find Interpretable LLM Feature Circuits

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.469627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaf86cd0-e337-456e-8a56-29e124281839 · outbound

This paper cites TinyStories: How Small Can Language Models Be and Still Speak Coherent English?.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models TinyStories: How Small Can Language Models Be and Still Speak Coherent English?

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.474085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7178c337-bf4e-46a1-a006-913578813a84 · outbound

This paper cites A mathematical framework for transformer circuits, 2021.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models A mathematical framework for transformer circuits, 2021

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.444187Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 369128b1-19b1-450b-a883-e88add6235ad · outbound

This paper cites J., Liao, I., Gurnee, W., and Tegmark, M.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models J., Liao, I., Gurnee, W., and Tegmark, M

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.552647Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0fbea687-ec13-4507-a204-5298dea91d5b · outbound

This paper cites D., Tillman, H., Goh, G., Troll, R., Radford, A., Sutskever, I., Leike, J., and Wu, J.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models D., Tillman, H., Goh, G., Troll, R., Radford, A., Sutskever, I., Leike, J., and Wu, J

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.424747Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 522e24f5-217d-44a6-b183-1b8aff6f0eab · outbound

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

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Automatically Identifying Local and Global Circuits with Linear Computation Graphs

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.652517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e7c6fd6-46b2-4f10-8fc0-fe92a225119f · outbound

This paper cites Gemma 2: Improving Open Language Models at a Practical Size.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Gemma 2: Improving Open Language Models at a Practical Size

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.712221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 98b75e5c-0694-4eb6-9e01-3d12c397fe86 · outbound

This paper cites Accelerating sparse autoencoder training via layer-wise transfer learning in large language models.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Accelerating sparse autoencoder training via layer-wise transfer learning in large language models

Reference 15

Resolution: verified exact; doi, observed 2026-08-09T10:11:51.966007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 91727d6c-73c4-4a18-b1fc-7659dbd1fad0 · outbound

This paper cites Language Models Represent Space and Time.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Language Models Represent Space and Time

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.752448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7226ec3c-01f7-4cce-abce-cef58a291205 · outbound

This paper cites Finding neurons in a haystack: Case studies with sparse probing.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Finding neurons in a haystack: Case studies with sparse probing

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.411395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation c5dd6416-b854-4c5a-80fe-6d72137b05a6 · outbound

This paper cites Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.760053Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d64d0a96-a696-4745-80fe-2af859f96d1f · outbound

This paper cites Random open problems.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Random open problems

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.399370Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 3eaf50f9-ab4e-48a8-a132-b22b001828b1 · outbound

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

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.766856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c132b4d8-b1b0-47e4-ad7c-4f229fd93528 · outbound

This paper cites Sparse crosscoders for cross-layer features and model diffing, 2024.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Sparse crosscoders for cross-layer features and model diffing, 2024

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.388484Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation b6f5904a-073e-4b41-8df6-b5af9e22a9b1 · outbound

This paper cites k-Sparse Autoencoders.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models k-Sparse Autoencoders

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.773693Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02ba2ab7-be1f-4936-ab0d-f1fef178fe0b · outbound

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

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.777585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 93bbec5a-e5f4-4230-90fe-d52523a6e18c · outbound

This paper cites J., Belinkov, Y., Bau, D., and Mueller, A.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models J., Belinkov, Y., Bau, D., and Mueller, A

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.375920Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 61068ed2-927c-4436-a78c-a9784e7cfa1b · outbound

This paper cites The Hydra Effect: Emergent Self-repair in Language Model Computations.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models The Hydra Effect: Emergent Self-repair in Language Model Computations

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.784564Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 56267dcb-dd2e-4000-a611-11d1caf9b6a5 · outbound

This paper cites Linguistic regularities in continuous space word representations.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Linguistic regularities in continuous space word representations

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.364819Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 858e0fbc-f649-4593-8231-15c248d939dc · outbound

This paper cites B., Lozhkov, A., Mitchell, M., Raffel, C., Werra, L.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models B., Lozhkov, A., Mitchell, M., Raffel, C., Werra, L

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.791856Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e45417b-291a-4d4a-bced-9d75e75a561d · outbound

This paper cites Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.796172Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b6425fa9-13d0-4158-93f9-df0ecb62edbb · outbound

This paper cites L., McDougall, C., MacDiarmid, M., Freeman, C.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models L., McDougall, C., MacDiarmid, M., Freeman, C

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.799408Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad94b412-6405-4d55-bf05-16fa3d71fbee · outbound

This paper cites Towards universality: Studying mechanistic similarity across language model architectures.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Towards universality: Studying mechanistic similarity across language model architectures

Reference 30

Resolution: verified fuzzy; raw_fallback, observed 2026-08-09T10:11:52.340927Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 4fe54092-f937-4040-8c7d-294d134c76d3 · outbound

This paper cites Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-08-09T10:11:52.174690Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.

Observation 89cf2cd1-53ed-49ba-ae76-d9963ae7c568 · outbound

This paper cites write newline.

Analyze Feature Flow to Enhance Interpretation and Steering in Language Models write newline

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-09T10:11:51.810083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation ddfb11d5-5e35-48ce-a91a-85dc7bfd7db5 · inbound

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies cites this paper.

FaithfulSAE: Towards Capturing Faithful Features with Sparse Autoencoders without External Dataset Dependencies Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T23:35:06.626592Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99c2055d-f6ed-4653-a0f4-30634d1cf8bd · inbound

Cross-Layer Discrete Concept Discovery for Interpreting Language Models cites this paper.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.984298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9504ce52-0529-4479-a0d4-d0e2c48eabff · inbound

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders cites this paper.

Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Reference 17

Resolution: verified exact; arxiv_id, observed 2026-06-27T10:40:49.821238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.