Paper Citation Record · LEDGER

On Linear Representations and Pretraining Data Frequency in Language Models

As of 17 August 2026, this Paper Citation Record lists 62 of 62 outbound references and 4 inbound Pith citation observations for arXiv:2504.12459.

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

pith.paper-citation-record.v1
2504.12459 v1

Coverage vector

measured 62 of 62 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-16T12:37:36.423808Z

measured 66 of 66 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-16T06:30:59.297886+00:00

measured 4 of 4 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-02T04:52:44.489356Z

measured 0 of 1 external citation measurements

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

Source: arxiv_reference, observed 2026-05-18T11:06:17.562742Z

Reference resolution

62 of 62 outbound references displayed

verified exact3
verified fuzzy15
unresolved43
parse uncertain0
malformed identifier1
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 9be8aa00-ec8e-4c84-a732-a1276b6a6208 · outbound

This paper cites To code or not to code? exploring impact of code in pre-training.

On Linear Representations and Pretraining Data Frequency in Language Models To code or not to code? exploring impact of code in pre-training

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:37.117127Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 02a38762-7b87-431e-b172-30f41c838d6e · outbound

This paper cites Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers.

On Linear Representations and Pretraining Data Frequency in Language Models Hacking smart machines with smarter ones: How to extract meaningful data from machine learning classifiers

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.222599Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 724aa831-5196-4c4f-aeb0-9e158903b4bb · outbound

This paper cites Interpreting Neural Networks through the Polytope Lens.

On Linear Representations and Pretraining Data Frequency in Language Models Interpreting Neural Networks through the Polytope Lens

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.225333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 65ade467-bb03-444d-a049-8e60da7558cc · outbound

This paper cites Membership inference attacks from first principles.

On Linear Representations and Pretraining Data Frequency in Language Models Membership inference attacks from first principles

Reference 4

Resolution: verified exact; raw_fallback, observed 2026-08-16T12:37:36.734597Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 690dd01c-c5c6-44ff-bf86-1a0bb0f9daa4 · outbound

This paper cites Quantifying memorization across neural language models.

On Linear Representations and Pretraining Data Frequency in Language Models Quantifying memorization across neural language models

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.232547Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abe70b6b-8a87-4ac0-9423-9ec506a8e51b · outbound

This paper cites How do large language models acquire factual knowledge during pretraining? In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024.

On Linear Representations and Pretraining Data Frequency in Language Models How do large language models acquire factual knowledge during pretraining? In The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:37.098171Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 82581bb6-349b-49d6-9b5a-b1a531e61b08 · outbound

This paper cites Identifying Linear Relational Concepts in Large Language Models.

On Linear Representations and Pretraining Data Frequency in Language Models Identifying Linear Relational Concepts in Large Language Models

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.239229Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d208efe-cb70-4887-a0ca-c1b5a09a3ad8 · outbound

This paper cites Recurrent neural networks learn to store and generate sequences using non-linear representations.

On Linear Representations and Pretraining Data Frequency in Language Models Recurrent neural networks learn to store and generate sequences using non-linear representations

Reference 8

Resolution: verified exact; doi, observed 2026-08-16T12:37:36.572317Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 296226ad-19b5-4b10-944c-4f34e5d2946c · outbound

This paper cites Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals.

On Linear Representations and Pretraining Data Frequency in Language Models Amnesic Probing: Behavioral Explanation with Amnesic Counterfactuals

Reference 9

Resolution: malformed identifier; no resolver link, observed 2026-08-16T12:37:36.245789Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c29e93ab-2b3d-42e3-9d62-b4b8eb55e9a7 · outbound

This paper cites Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions.

On Linear Representations and Pretraining Data Frequency in Language Models Measuring Causal Effects of Data Statistics on Language Model's `Factual' Predictions

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.248759Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dff16e97-9766-4084-9ddf-47eae3b4dde7 · outbound

This paper cites Smith, and Jesse Dodge.

On Linear Representations and Pretraining Data Frequency in Language Models Smith, and Jesse Dodge

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:37.085232Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 2128fed1-42a8-4911-864c-38476d366370 · outbound

This paper cites A mathematical framework for transformer circuits.

On Linear Representations and Pretraining Data Frequency in Language Models A mathematical framework for transformer circuits

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.255407Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9573e36-13d2-474b-9126-440c4b4dfe71 · outbound

This paper cites T - RE x: A large scale alignment of natural language with knowledge base triples.

On Linear Representations and Pretraining Data Frequency in Language Models T - RE x: A large scale alignment of natural language with knowledge base triples

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:37.067881Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b27cfc5b-8070-4529-8f6b-b4934ec0c0ac · outbound

This paper cites Towards Understanding Linear Word Analogies.

On Linear Representations and Pretraining Data Frequency in Language Models Towards Understanding Linear Word Analogies

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.261244Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec363ae7-6085-4fd0-8ed9-1d9c0af324bc · outbound

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

On Linear Representations and Pretraining Data Frequency in Language Models The Pile: An 800GB Dataset of Diverse Text for Language Modeling

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.264651Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16ecfce0-7101-4a7e-b91e-ef1b3bd77a7f · outbound

This paper cites Scaling and evaluating sparse autoencoders.

On Linear Representations and Pretraining Data Frequency in Language Models Scaling and evaluating sparse autoencoders

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.268775Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dacfa710-47cd-4a08-a7fc-71c7dafc86e4 · outbound

This paper cites What can transformers learn in-context? a case study of simple function classes.

On Linear Representations and Pretraining Data Frequency in Language Models What can transformers learn in-context? a case study of simple function classes

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:37.048571Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 8011d74e-f40c-4da3-a142-ecbac4602b57 · outbound

This paper cites Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn`t.

On Linear Representations and Pretraining Data Frequency in Language Models Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn`t

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.276369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0f6d728a-31b0-4b19-b183-0614e70e8c81 · outbound

This paper cites OLM o: Accelerating the science of language models.

On Linear Representations and Pretraining Data Frequency in Language Models OLM o: Accelerating the science of language models

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.280450Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61de6d86-90cd-4feb-8723-69a9970c8ba9 · outbound

This paper cites an unresolved cited work.

On Linear Representations and Pretraining Data Frequency in Language Models Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-08-16T12:37:37.036827Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation fc1f87f2-39a9-495b-94b9-fdc8f5cd209b · outbound

This paper cites In- Context Learning Creates Task Vectors.

On Linear Representations and Pretraining Data Frequency in Language Models In- Context Learning Creates Task Vectors

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.287788Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 935a2fb3-0694-45eb-8236-cd6caac42e6d · outbound

This paper cites Linearity of relation decoding in transformer language models.

On Linear Representations and Pretraining Data Frequency in Language Models Linearity of relation decoding in transformer language models

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.292061Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef2593e1-8db3-4dca-af3f-113b8d36f760 · outbound

This paper cites Sparse autoencoders find highly interpretable features in language models.

On Linear Representations and Pretraining Data Frequency in Language Models Sparse autoencoders find highly interpretable features in language models

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.294958Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1820c1dd-5bb4-4953-ad68-da5d79e0ca4a · outbound

This paper cites On the origins of linear representations in large language models.

On Linear Representations and Pretraining Data Frequency in Language Models On the origins of linear representations in large language models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:37.010624Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 28864f5b-e906-4a6e-9f25-80469d09aa74 · outbound

This paper cites an unresolved cited work.

On Linear Representations and Pretraining Data Frequency in Language Models Unresolved cited work

Reference 25

Resolution: verified exact; doi, observed 2026-08-16T12:37:36.528778Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 63c8a6f8-3f32-4c64-969c-15cb5e33744f · outbound

This paper cites Multilingual reliability and semantic structure of continuous word spaces.

On Linear Representations and Pretraining Data Frequency in Language Models Multilingual reliability and semantic structure of continuous word spaces

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.996973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 9646f0d9-ee4c-458e-8ced-9bf0aaa0b3ba · outbound

This paper cites A pretrainer`s guide to training data: Measuring the effects of data age, domain coverage, quality, & toxicity.

On Linear Representations and Pretraining Data Frequency in Language Models A pretrainer`s guide to training data: Measuring the effects of data age, domain coverage, quality, & toxicity

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.307341Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80ebb938-d5d8-4a12-b775-374d0ec56c21 · outbound

This paper cites At which training stage does code data help LLM s reasoning? In The Twelfth International Conference on Learning Representations, 2024.

On Linear Representations and Pretraining Data Frequency in Language Models At which training stage does code data help LLM s reasoning? In The Twelfth International Conference on Learning Representations, 2024

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.314919Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e08f2e27-05eb-4b4c-b93d-b3ca2e19131e · outbound

This paper cites When not to trust language models: Investigating effectiveness of parametric and non-parametric memories.

On Linear Representations and Pretraining Data Frequency in Language Models When not to trust language models: Investigating effectiveness of parametric and non-parametric memories

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.317695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5148ca2b-7301-431a-9bb8-06e8e79eb9c3 · outbound

This paper cites Embers of autoregression show how large language models are shaped by the problem they are trained to solve.

On Linear Representations and Pretraining Data Frequency in Language Models Embers of autoregression show how large language models are shaped by the problem they are trained to solve

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.320670Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7276c5e4-7105-4cd2-a26b-dbe878ecf07d · outbound

This paper cites Language models implement simple W ord2 V ec-style vector arithmetic.

On Linear Representations and Pretraining Data Frequency in Language Models Language models implement simple W ord2 V ec-style vector arithmetic

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.323521Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07fb214a-a2e4-4e3b-9bf2-a3ce395845e2 · outbound

This paper cites Efficient Estimation of Word Representations in Vector Space.

On Linear Representations and Pretraining Data Frequency in Language Models Efficient Estimation of Word Representations in Vector Space

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.326920Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d423fe4a-a934-4b57-b535-2dd7941ac934 · outbound

This paper cites Distributed representations of words and phrases and their compositionality.

On Linear Representations and Pretraining Data Frequency in Language Models Distributed representations of words and phrases and their compositionality

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.970610Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c8898bc0-9f6a-4d58-8c0b-a8504aaba89c · outbound

This paper cites an unresolved cited work.

On Linear Representations and Pretraining Data Frequency in Language Models Unresolved cited work

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.333747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 002554d9-8b63-4da5-9dec-f759a6602b8c · outbound

This paper cites Zoom in: An introduction to circuits.

On Linear Representations and Pretraining Data Frequency in Language Models Zoom in: An introduction to circuits

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.959877Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation f021bf14-4dde-4a74-9088-6eb57540e730 · outbound

This paper cites Chatterji, Faisal Ladhak, and Tatsunori Hashimoto.

On Linear Representations and Pretraining Data Frequency in Language Models Chatterji, Faisal Ladhak, and Tatsunori Hashimoto

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.341261Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c529b3bc-2e8f-452b-bdf4-4a5c14891550 · outbound

This paper cites Learning Hierarchical Structures with Linear Relational Embedding.

On Linear Representations and Pretraining Data Frequency in Language Models Learning Hierarchical Structures with Linear Relational Embedding

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.940678Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 059f7a5b-ed0e-4560-abea-b6611f4a5ae9 · outbound

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

On Linear Representations and Pretraining Data Frequency in Language Models The Linear Representation Hypothesis and the Geometry of Large Language Models

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.929566Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 78bf24e7-b5fc-47f4-98f7-6dbc93b669ab · outbound

This paper cites G lo V e: Global vectors for word representation.

On Linear Representations and Pretraining Data Frequency in Language Models G lo V e: Global vectors for word representation

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.352815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8e3a177-e391-4a5d-b57d-a290d40dad70 · outbound

This paper cites Null it out: Guarding protected attributes by iterative nullspace projection.

On Linear Representations and Pretraining Data Frequency in Language Models Null it out: Guarding protected attributes by iterative nullspace projection

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.917292Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a78393f9-dd28-4252-89bc-4b33ca76a95d · outbound

This paper cites Impact of pretraining term frequencies on few-shot numerical reasoning.

On Linear Representations and Pretraining Data Frequency in Language Models Impact of pretraining term frequencies on few-shot numerical reasoning

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.359724Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77363836-c1b2-4098-b3eb-386f16046404 · outbound

This paper cites Backtracking mathematical reasoning of language models to the pretraining data.

On Linear Representations and Pretraining Data Frequency in Language Models Backtracking mathematical reasoning of language models to the pretraining data

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.905434Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 439fd0fe-b768-4db5-8271-0a4eea112db9 · outbound

This paper cites Steering llama 2 via contrastive activation addition.

On Linear Representations and Pretraining Data Frequency in Language Models Steering llama 2 via contrastive activation addition

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.365962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f2046014-23a3-4e24-a48e-82f066f28c8c · outbound

This paper cites Salton, A.

On Linear Representations and Pretraining Data Frequency in Language Models Salton, A

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.369689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd67bddf-8ca1-4c1e-b87e-44f74ebb32a4 · outbound

This paper cites an unresolved cited work.

On Linear Representations and Pretraining Data Frequency in Language Models Unresolved cited work

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.372202Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3f630405-b32b-49dd-a1de-c818931f275e · outbound

This paper cites The bias amplification paradox in text-to-image generation.

On Linear Representations and Pretraining Data Frequency in Language Models The bias amplification paradox in text-to-image generation

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.375367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f37685d7-e8c3-4065-99d2-e447deaff3da · outbound

This paper cites Detecting pretraining data from large language models.

On Linear Representations and Pretraining Data Frequency in Language Models Detecting pretraining data from large language models

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.378430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 707bccd1-206e-49a4-ad5f-103f29e67cc9 · outbound

This paper cites Membership inference attacks against machine learning models.

On Linear Representations and Pretraining Data Frequency in Language Models Membership inference attacks against machine learning models

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.381493Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8bdb9137-e7d0-4ed3-b297-acb6ea1f6d2a · outbound

This paper cites The curious case of hallucinatory (un)answerability: Finding truths in the hidden states of over-confident large language models.

On Linear Representations and Pretraining Data Frequency in Language Models The curious case of hallucinatory (un)answerability: Finding truths in the hidden states of over-confident large language models

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.385139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87c6a1e0-ac1d-4729-875f-966a3e12ef57 · outbound

This paper cites Dolma: an open corpus of three trillion tokens for language model pretraining research.

On Linear Representations and Pretraining Data Frequency in Language Models Dolma: an open corpus of three trillion tokens for language model pretraining research

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.388267Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8182546-7004-4d5e-b677-b7a59e917a92 · outbound

This paper cites Extracting Latent Steering Vectors from Pretrained Language Models.

On Linear Representations and Pretraining Data Frequency in Language Models Extracting Latent Steering Vectors from Pretrained Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.390855Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3bf08ac5-ee0c-47ea-af86-ba018a230d97 · outbound

This paper cites Formalizing and Estimating Distribution Inference Risks.

On Linear Representations and Pretraining Data Frequency in Language Models Formalizing and Estimating Distribution Inference Risks

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.393954Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab1dba8d-4911-47ac-b555-1fe3ce592346 · outbound

This paper cites Scaling Monosemanticity : Extracting Interpretable Features from Claude 3 Sonnet.

On Linear Representations and Pretraining Data Frequency in Language Models Scaling Monosemanticity : Extracting Interpretable Features from Claude 3 Sonnet

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.880815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation c10e049a-c1a9-429b-a62f-f7d6d78e05fd · outbound

This paper cites Function vectors in large language models.

On Linear Representations and Pretraining Data Frequency in Language Models Function vectors in large language models

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.399886Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 980dfd8b-4b2f-4b44-866e-321f219ce919 · outbound

This paper cites GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model.

On Linear Representations and Pretraining Data Frequency in Language Models GPT-J-6B: A 6 Billion Parameter Autoregressive Language Model

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.402311Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d105eac-e5ca-42f4-b4de-233b54968e97 · outbound

This paper cites Understanding reasoning ability of language models from the perspective of reasoning paths aggregation.

On Linear Representations and Pretraining Data Frequency in Language Models Understanding reasoning ability of language models from the perspective of reasoning paths aggregation

Reference 56

Resolution: verified fuzzy; raw_fallback, observed 2026-08-16T12:37:36.855643Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation a2631398-a306-4511-9fc1-44dc66fb242d · outbound

This paper cites Generalization v.s.

On Linear Representations and Pretraining Data Frequency in Language Models Generalization v.s

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.408579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f03f27a-ce68-4dbd-8a02-dd110def5698 · outbound

This paper cites Doremi: Optimizing data mixtures speeds up language model pretraining.

On Linear Representations and Pretraining Data Frequency in Language Models Doremi: Optimizing data mixtures speeds up language model pretraining

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.411183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c1b8bedb-0c0b-4e4e-aca8-801ac0042f62 · outbound

This paper cites write newline.

On Linear Representations and Pretraining Data Frequency in Language Models write newline

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.413796Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10cc502b-2936-448a-a369-1dcf261fe555 · outbound

This paper cites @esa (Ref.

On Linear Representations and Pretraining Data Frequency in Language Models @esa (Ref

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.417232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f53c3e7-0937-4ab4-9c36-cbe7f4006e84 · outbound

This paper cites an unresolved cited work.

On Linear Representations and Pretraining Data Frequency in Language Models Unresolved cited work

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.420669Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fd38eb4-93c0-4589-96fe-51cfee1bf51e · outbound

This paper cites an unresolved cited work.

On Linear Representations and Pretraining Data Frequency in Language Models Unresolved cited work

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-16T12:37:36.423808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation eb9371a3-71e5-430c-a26b-c3960bc65be3 · inbound

How Do Language Models Compose Functions? cites this paper.

How Do Language Models Compose Functions? On Linear Representations and Pretraining Data Frequency in Language Models

Reference 29

Resolution: verified exact; arxiv_id, observed 2026-05-18T11:06:17.566205Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation b4298fba-acae-4c14-886a-9dc5eb2345b5 · inbound

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space cites this paper.

Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space On Linear Representations and Pretraining Data Frequency in Language Models

Reference 150

Resolution: metadata mismatch; arxiv_id, observed 2026-05-13T05:27:19.242265Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.

Observation 72086d85-fd50-4d02-ae8f-6cd0aac35639 · inbound

Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering cites this paper.

Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering On Linear Representations and Pretraining Data Frequency in Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-02T04:52:44.489356Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e530c710-5451-478f-b005-66aa643c563f · inbound

Bridging Compute- and Data-Optimal Pretraining cites this paper.

Bridging Compute- and Data-Optimal Pretraining On Linear Representations and Pretraining Data Frequency in Language Models

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-01T03:02:05.090555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.