Paper Citation Record · LEDGER

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning

As of 19 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2411.10397.

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

pith.paper-citation-record.v1
2411.10397 v2

Coverage vector

measured 28 of 28 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-12T19:45:19.777065Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00

measured 1 of 1 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-09T20:18:31.022982Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-09T20:18:31.450784Z

Reference resolution

28 of 28 outbound references displayed

verified exact1
verified fuzzy0
unresolved27
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation b55bdfbd-4a98-43ca-87fc-1a38eae02d49 · outbound

This paper cites Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.549270Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61dbd987-a92e-44a1-9162-9fc8afc5d3bb · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.561559Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fc0192e-eec1-4f3f-85d5-3f5ab148493e · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:45:20.476494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 47e1ee64-ea68-4c64-9754-6047c13b1ded · outbound

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

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.576661Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d52736f2-af47-4904-ba30-8f8f7e614253 · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 5

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:45:20.454900Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1c1ffe36-e905-4dcc-89be-bdc91c304feb · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.592947Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02fcf25d-05cd-4735-ae44-b62d52b47e67 · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Scaling and evaluating sparse autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.598994Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0525e6f5-55fa-40ad-a296-942785ca235e · outbound

This paper cites Evaluating Synthetic Activations composed of SAE Latents in GPT-2.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Evaluating Synthetic Activations composed of SAE Latents in GPT-2

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-08-12T19:45:20.231430Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation d30135d5-b274-43c5-9fa3-e2bf759c22aa · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 9

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:45:20.414275Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 954f25b0-dd46-4ed5-a973-41e1a85ce274 · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:45:20.392907Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation c9b96297-d1e9-4632-b58e-b4cbff094f6d · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 11

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:45:20.359489Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation e9f3c411-fec2-4efe-a787-84e450f2214b · outbound

This paper cites Inference-Time Intervention: Eliciting Truthful Answers from a Language Model.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.640112Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ecf5f91-188f-493b-9de6-bc92361af7ec · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 13

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:45:20.336337Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 6f5ab4d7-6d93-4f40-b98c-b6574e436a6f · outbound

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

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.656613Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e45010d8-e77a-4492-be6b-5609c78bc8a4 · outbound

This paper cites Efficient Dictionary Learning with Switch Sparse Autoencoders.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Efficient Dictionary Learning with Switch Sparse Autoencoders

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.665822Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9707975-4f44-4618-bfef-8bed2cda3b6a · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-08-12T19:45:20.310516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.

Observation 1e90f9ec-9985-4e8d-9b26-367a837f4bdb · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Steering Llama 2 via Contrastive Activation Addition

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.678375Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0790984e-28c1-45fd-8b5c-cd2cd962ff66 · outbound

This paper cites The Geometry of Categorical and Hierarchical Concepts in Large Language Models.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning The Geometry of Categorical and Hierarchical Concepts in Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.684648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd115475-3355-4902-9a50-fe203ad678ec · outbound

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

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.692933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3749fc7-30eb-4a1c-b6a2-475d0ce47a43 · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.700933Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fae45a25-9f29-49a1-b168-5a1c98a1bb7f · outbound

This paper cites Improving Dictionary Learning with Gated Sparse Autoencoders.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Improving Dictionary Learning with Gated Sparse Autoencoders

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.712648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 86d73ac7-f590-478a-89d0-4b0f8df43730 · outbound

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

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Jumping Ahead: Improving Reconstruction Fidelity with JumpReLU Sparse Autoencoders

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.723321Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b0879f4-a22b-4722-84ea-e0cc99692ae5 · outbound

This paper cites an unresolved cited work.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.730728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a5d1b57a-3890-4e60-bc7d-c41e19b2c4af · outbound

This paper cites Attribution Patching Outperforms Automated Circuit Discovery.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Attribution Patching Outperforms Automated Circuit Discovery

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.741219Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 907b4804-6321-497d-b932-5920a585f7d1 · outbound

This paper cites Daniel Freeman, Theodore R.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Daniel Freeman, Theodore R

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.747654Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0a7234b3-e9be-4090-a1be-7556d4490e48 · outbound

This paper cites Steering Language Models With Activation Engineering.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning Steering Language Models With Activation Engineering

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.761538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f4cf88a-936e-4da5-b97d-f35df7820f25 · outbound

This paper cites online" 'onlinestring :=.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning online" 'onlinestring :=

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.768482Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 605bb4b3-bf2b-40ae-9001-9655d54ef950 · outbound

This paper cites write newline.

Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning write newline

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-12T19:45:19.777065Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation aee6e5eb-cb38-4ad8-a0ca-b5238e4a994b · inbound

Low-Rank Adapting Models for Sparse Autoencoders cites this paper.

Low-Rank Adapting Models for Sparse Autoencoders Features that Make a Difference: Leveraging Gradients for Improved Dictionary Learning

Reference 25

Resolution: verified exact; local_arxiv, observed 2026-08-09T20:18:31.468811Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.