Paper Citation Record · LEDGER

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models

As of 8 August 2026, this Paper Citation Record lists 40 of 40 outbound references and 4 inbound Pith citation observations for arXiv:2506.00653.

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

pith.paper-citation-record.v1
2506.00653 v3

Coverage vector

measured 40 of 40 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-07T12:07:12.195614Z

measured 44 of 44 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 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-05T10:17:13.117220Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-07-02T08:16:47.723815Z

Reference resolution

40 of 40 outbound references displayed

verified exact1
verified fuzzy15
unresolved23
parse uncertain0
malformed identifier0
metadata mismatch1

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 71a66a4d-1d65-4ef3-8742-eaab81d6aca7 · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Refusal in Language Models Is Mediated by a Single Direction

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:09.147565Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1853f68c-b9e1-447d-b13f-92231db45124 · outbound

This paper cites Revisiting model stitching to compare neural representations.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Revisiting model stitching to compare neural representations

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:16.061940Z

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 4e11166d-3e79-44f6-b5b2-65be13bc0482 · outbound

This paper cites Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Towards Cross-Tokenizer Distillation: the Universal Logit Distillation Loss for LLMs

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:09.286384Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 068618f1-6652-41dc-9e8b-c4d05f3b8642 · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Towards monosemanticity: Decomposing language models with dictionary learning

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:09.386595Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23488e73-c4a0-4368-bb38-b4274ce3b555 · outbound

This paper cites Curve circuits.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Curve circuits

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:15.910916Z

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 fdd7fd8f-625c-44fe-a744-18425836d52b · outbound

This paper cites Similarity and matching of neural network representations.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Similarity and matching of neural network representations

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:15.758563Z

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 54bd986e-1009-46cc-a431-39829c0c8e44 · outbound

This paper cites A mathematical framework for transformer circuits.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models A mathematical framework for transformer circuits

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:09.661210Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 542c91c9-630b-4f7f-8dc1-3b870637948d · outbound

This paper cites Toy models of superposition.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Toy models of superposition

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:15.599874Z

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 181f0547-4cf8-4b1f-828b-6b90458c181d · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:09.798719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a889b737-5291-43d4-b07a-806665e48ffb · outbound

This paper cites Universal neurons in gpt2 language models.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Universal neurons in gpt2 language models

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:15.444373Z

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 d6e9f57c-9577-4bfe-b046-bb0c33310f70 · outbound

This paper cites Saes are highly dataset dependent: A case study on the refusal direction.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Saes are highly dataset dependent: A case study on the refusal direction

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:15.255568Z

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 ad37495f-aa31-4b3c-b907-660b392b9047 · outbound

This paper cites Towards Measuring Representational Similarity of Large Language Models.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Towards Measuring Representational Similarity of Large Language Models

Reference 12

Resolution: verified exact; local_arxiv, observed 2026-08-07T12:07:13.440934Z

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 30372933-9dce-4e6e-a68f-9fec3583b8aa · outbound

This paper cites Similarity of neural network models: A survey of functional and representational measures.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Similarity of neural network models: A survey of functional and representational measures

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:15.115350Z

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 78737e0f-a994-4e71-b8c7-4da7f55010ad · outbound

This paper cites ReSi: A Comprehensive Benchmark for Representational Similarity Measures.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models ReSi: A Comprehensive Benchmark for Representational Similarity Measures

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-08-07T12:07:13.279213Z

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 3dca8ab0-46ef-4f01-a261-4dfd211b2333 · outbound

This paper cites Similarity of Neural Network Representations Revisited.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Similarity of Neural Network Representations Revisited

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.243871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 812f38d5-6cd1-4929-875a-da40cf98fb9d · outbound

This paper cites The Remarkable Robustness of LLMs: Stages of Inference?.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models The Remarkable Robustness of LLMs: Stages of Inference?

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.354834Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5976de11-95bb-44e3-859e-f70e38f5db6c · outbound

This paper cites Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.417992Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 804b3db4-8e99-435d-a6c0-0ffb280dc208 · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.502533Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d2338b6-bcfe-475d-9da8-5810a2ba536f · outbound

This paper cites URL https://transformer-circuits.pub/2024/crosscoders/index.html.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models URL https://transformer-circuits.pub/2024/crosscoders/index.html

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:14.902151Z

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 4a9a8fef-6870-4662-95a8-d5bcde2bd181 · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.667466Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ed5e59d7-52f9-433a-b7ff-b5ed70cd1a96 · outbound

This paper cites Linearly Mapping from Image to Text Space.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Linearly Mapping from Image to Text Space

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.760990Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 27ff1048-9e8f-4700-9b80-446a185067cf · outbound

This paper cites Cross-tokenizer distillation via approximate likelihood matching.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Cross-tokenizer distillation via approximate likelihood matching

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.807782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4ab05bc6-bfe5-4cfd-bc63-ae374bf2e0f2 · outbound

This paper cites Neuronpedia, 2025.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Neuronpedia, 2025

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:14.719020Z

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 731a14c1-d67b-46ff-be42-d98e11d29951 · outbound

This paper cites Activation space interventions can be transferred between large language models.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Activation space interventions can be transferred between large language models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:10.953188Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 243b6ac9-53e5-4a7a-92ee-4615b3a3f462 · outbound

This paper cites Steering Llama 2 via Contrastive Activation Addition.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Steering Llama 2 via Contrastive Activation Addition

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:11.081727Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f0e4ff69-eb6b-45ca-8c01-3f0ae753a251 · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:11.137675Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e965a90-148b-4552-a43c-0fb40882799b · outbound

This paper cites Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Svcca: Singular vector canonical correlation analysis for deep learning dynamics and interpretability

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:14.562404Z

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 6277cc14-4c32-40b8-8d28-c0c1025b0305 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Steering llama 2 via contrastive activation addition

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:14.371582Z

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 bac696bb-bc2b-4a50-bb1d-756bd26114c8 · outbound

This paper cites High-low frequency detectors.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models High-low frequency detectors

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:14.201282Z

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 bf416959-719e-4dd2-8b26-d21fcb152e1c · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Improving Instruction-Following in Language Models through Activation Steering

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:11.509790Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 092ae948-46ad-449a-85c3-f1f98c2b5b38 · outbound

This paper cites Analysing the generalisation and reliability of steering vectors.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Analysing the generalisation and reliability of steering vectors

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:14.088723Z

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 dfcabeb0-d753-4d5a-9560-76b03b72702f · outbound

This paper cites Hashimoto.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Hashimoto

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:11.660484Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3dd77334-8c0e-4bd9-8186-cddb362d7f7c · outbound

This paper cites Steering Language Models With Activation Engineering.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Steering Language Models With Activation Engineering

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:11.742179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d09cd282-1a87-4730-8dfb-114bb3378dab · outbound

This paper cites Knowledge Fusion of Large Language Models.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Knowledge Fusion of Large Language Models

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:11.805248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9264869d-b344-4858-9f8f-8a172d8fd44b · outbound

This paper cites Hopcroft.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Hopcroft

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:13.916585Z

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 a44a648d-3daf-4ca6-80dc-25d7bcf6f345 · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:11.939328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5dbf071c-3e88-4dcc-9fa6-e6ef100916d9 · outbound

This paper cites Deep Model Reassembly.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Deep Model Reassembly

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:11.998231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61d6c3d7-4da1-4053-bda2-f7419232eed3 · outbound

This paper cites P Xing, Joseph E.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models P Xing, Joseph E

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:12.071091Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 308d5208-37dc-4c4b-bcac-2b83e1a16e8b · outbound

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

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-07T12:07:12.114429Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d05920c-ae7d-4d9a-b25a-1477954613bd · outbound

This paper cites Zico Kolter, and Matt Fredrikson.

Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models Zico Kolter, and Matt Fredrikson

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-07T12:07:13.691534Z

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.

Pith citing papers

Observation 0fc98fd8-5782-41cf-a7c4-f2945f1edad8 · inbound

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment cites this paper.

The Master Key Hypothesis: Unlocking Cross-Model Capability Transfer via Linear Subspace Alignment Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models

Reference 9

Resolution: verified exact; arxiv_id, observed 2026-05-11T00:15:56.149206Z

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 4162988a-02e1-4a80-8dd0-8f0f308515bf · inbound

HyperTransport: Amortized Conditioning of T2I Generative Models cites this paper.

HyperTransport: Amortized Conditioning of T2I Generative Models Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models

Reference 1

Resolution: verified exact; arxiv_id, observed 2026-05-12T07:46:38.048741Z

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 c513d267-dd03-40cc-ba38-b2d9c5ca2870 · inbound

Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation cites this paper.

Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models

Reference 7

Resolution: metadata mismatch; arxiv_id, observed 2026-07-02T08:16:47.725232Z

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 04dfa064-c0a2-43b8-9fc6-10db9eb3cc33 · inbound

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse cites this paper.

Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-05T10:17:13.117220Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.