Paper Citation Record · LEDGER

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering

As of 9 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:2505.15038.

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

pith.paper-citation-record.v1
2505.15038 v2

Coverage vector

measured 29 of 29 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T15:30:22.804927Z

measured 29 of 29 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-08T06:32:00.761636+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

29 of 29 outbound references displayed

verified exact1
verified fuzzy0
unresolved28
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c4a512aa-97f5-420f-847b-66e00b28f24a · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Understanding intermediate layers using linear classifier probes

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:20.574425Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b98db61-803d-43f1-a45c-ce8a3ff174e7 · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:20.624619Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f767a57a-6f27-4a8c-ad8d-774bb4ee4c83 · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:20.661697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9c8e84e3-b568-4947-9b8a-9ba528f8ad9b · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 4

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:30:24.105150Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation acf4663b-dc61-4218-9511-4a37b9e26459 · outbound

This paper cites Toy Models of Superposition.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Toy Models of Superposition

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:20.805089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c04119bf-2f90-4b9f-8b3f-e5df7b6030ed · outbound

This paper cites Scaling and evaluating sparse autoencoders.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Scaling and evaluating sparse autoencoders

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:20.901633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 94e961d9-3a53-49b2-8fec-3af767e6ca5e · outbound

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

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:20.974878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d424c4f7-32fd-4dcd-9201-c843b9405c1e · outbound

This paper cites SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.080448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2e96da92-1044-4c69-b58c-6500163e9fcd · outbound

This paper cites Improving Activation Steering in Language Models with Mean-Centring.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Improving Activation Steering in Language Models with Mean-Centring

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.140538Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cd22533b-9f6c-49ed-b795-351f9708191c · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 10

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:30:23.972516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation abe22b27-7cb0-4906-9c8a-b4bb8757cb0f · outbound

This paper cites Style Vectors for Steering Generative Large Language Model.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Style Vectors for Steering Generative Large Language Model

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.230674Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c715f19e-34da-45d1-9d25-d3b0fab4ab85 · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.276165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 201a46ff-68fa-4b96-95bd-71bb9cfebe6b · outbound

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

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.356728Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fcc47d5e-3a73-4988-8fc7-f3ca0ca8939a · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 14

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:30:23.793886Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation e6aee399-47a2-4221-90da-cf60498f4283 · outbound

This paper cites In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.522969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d9277a90-7d53-45b4-a424-402393b8b4df · outbound

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

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.599322Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3424a7f0-ba9a-476c-ada1-b166908d5378 · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 17

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:30:23.660873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4820c29c-ea39-43c9-9093-cab79cc64f85 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Steering Llama 2 via Contrastive Activation Addition

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.739066Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b71ef92c-986b-492d-bf4c-c50c5a7a7587 · outbound

This paper cites Open Problems in Mechanistic Interpretability.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Open Problems in Mechanistic Interpretability

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.825428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87ed623a-6a64-4efb-94fa-1a8fbe0d7058 · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 20

Resolution: verified exact; raw_fallback, observed 2026-08-07T15:30:23.177980Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d070b568-4c8d-4f55-a4d4-d1f5b0a05c2b · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:21.972928Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07e0aa73-af02-4598-9da3-79196be7edc4 · outbound

This paper cites Improving Instruction-Following in Language Models through Activation Steering.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Improving Instruction-Following in Language Models through Activation Steering

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:22.087008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7de8091e-ac4c-4508-b0d3-378160996a71 · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:22.166542Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a9fc4e6-95b4-4fb6-a4ba-502bb7e25f20 · outbound

This paper cites AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:22.282961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 02064c76-1602-444d-b873-008b358aec07 · outbound

This paper cites Uncovering Latent Chain of Thought Vectors in Language Models.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Uncovering Latent Chain of Thought Vectors in Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:22.389509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37472da4-fdd5-45de-8e4e-444bc9b51b85 · outbound

This paper cites an unresolved cited work.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Unresolved cited work

Reference 26

Resolution: unresolved; raw_fallback, observed 2026-08-07T15:30:23.501130Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 82d1651b-11e6-416f-b5e6-6ca25a3eb113 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering Representation Engineering: A Top-Down Approach to AI Transparency

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:22.604271Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3fe23466-4c05-46bd-9a57-9b325f8c6c3b · outbound

This paper cites online" 'onlinestring :=.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering online" 'onlinestring :=

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:22.721748Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c374dd58-71b9-4f75-8c3f-01ec59ca538e · outbound

This paper cites write newline.

Denoising Concept Vectors with Sparse Autoencoders for Improved Language Model Steering write newline

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-07T15:30:22.804927Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.