Paper Citation Record · LEDGER

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models

As of 21 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 2 inbound Pith citation observations for arXiv:2501.15054.

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

pith.paper-citation-record.v1
2501.15054 v2

Coverage vector

measured 26 of 26 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-10T14:43:14.801525Z

measured 28 of 28 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-20T06:33:59.587034+00:00

measured 2 of 2 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-14T04:18:56.244847Z

measured 0 of 1 external citation measurements

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

Source: pith, observed 2026-08-06T18:59:33.160545Z

Reference resolution

26 of 26 outbound references displayed

verified exact0
verified fuzzy5
unresolved21
parse uncertain0
malformed identifier0
metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation c1f030de-aa82-4686-8c78-12fe3ae90242 · outbound

This paper cites Neel Nanda.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Neel Nanda

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:43:15.086106Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 268e257b-7345-4887-b610-8562bc4a4508 · outbound

This paper cites A review of taxonomies of explainable artificial intelligence (xai) methods.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models A review of taxonomies of explainable artificial intelligence (xai) methods

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:43:15.053253Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6729c272-5017-4a3e-9ebd-bec9fcd2f384 · outbound

This paper cites Mechanistic Interpretability for AI Safety -- A Review.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Mechanistic Interpretability for AI Safety -- A Review

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.729779Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d45590e-84b4-42de-b444-628aa8166c6b · outbound

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

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Sparse Autoencoders Find Highly Interpretable Features in Language Models

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.741505Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ac73ebc-e5f0-4645-b3e4-e0a97897b17c · outbound

This paper cites Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.745081Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 810515a5-3cf0-4547-ab2a-799b453335be · outbound

This paper cites Localizing Model Behavior with Path Patching.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Localizing Model Behavior with Path Patching

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.748803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 81f2b69b-d54c-4439-b631-24a4305e28c3 · outbound

This paper cites com/posts/AcKRB8wDpdaN6v6ru/interpreting-gpt-the-logit-lens.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models com/posts/AcKRB8wDpdaN6v6ru/interpreting-gpt-the-logit-lens

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:43:15.041894Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation fc23120f-5abd-491a-84ea-8dcc3276034f · outbound

This paper cites Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Still No Lie Detector for Language Models: Probing Empirical and Conceptual Roadblocks

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.759786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c8ba1d4b-b0f9-4cae-a9da-d4d1ec3d2dab · outbound

This paper cites Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.763946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7759ce2-4653-44f3-960e-f793910915cc · outbound

This paper cites Emergent Abilities of Large Language Models.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Emergent Abilities of Large Language Models

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.768096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 708a0b8d-41c3-4d26-896f-e0fd0c4471ad · outbound

This paper cites Progress measures for grokking via mechanistic interpretability.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Progress measures for grokking via mechanistic interpretability

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.771573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4382c841-0db5-4bfa-9031-dfca2a9091ca · outbound

This paper cites Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.775196Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e8a802a3-b2a4-4638-a89a-146c3af9cfb7 · outbound

This paper cites Locating and Editing Factual Associations in GPT.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Locating and Editing Factual Associations in GPT

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.779216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 860676fe-f804-4626-9fbf-632dacd16e3a · outbound

This paper cites A Survey of Machine Unlearning.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models A Survey of Machine Unlearning

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.782996Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80f97076-180f-4218-8226-8aef73db19aa · outbound

This paper cites Circumventing interpretability: How to defeat mind-readers.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Circumventing interpretability: How to defeat mind-readers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.786443Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8fee2dd8-deeb-431c-ac2d-e6ecb3d8d85e · outbound

This paper cites Discovering Latent Knowledge in Language Models Without Supervision.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Discovering Latent Knowledge in Language Models Without Supervision

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.789971Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 599be8c9-332f-4cc9-b99f-d2ca329015c0 · outbound

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

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Representation Engineering: A Top-Down Approach to AI Transparency

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.793410Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 85c92d42-2d8c-43e8-9bf8-053b56e0a0dc · outbound

This paper cites AI Deception: A Survey of Examples, Risks, and Potential Solutions.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models AI Deception: A Survey of Examples, Risks, and Potential Solutions

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.797897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d41b6da4-6911-4cac-9ea4-44a829bda27e · outbound

This paper cites An overview of 11 proposals for building safe advanced AI.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models An overview of 11 proposals for building safe advanced AI

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.801525Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cefe1f41-dc8d-4d9e-adfa-8be2419a5485 · outbound

This paper cites Neel Nanda.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Neel Nanda

Reference 2018

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:43:15.064000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 6f5ceadc-785c-4c56-9ca3-dcfbfba038f4 · outbound

This paper cites Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.756025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2552a8a-796f-4dd6-bef8-6f489b7c0018 · outbound

This paper cites Lee Sharkey, Sid Black, and beren.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Lee Sharkey, Sid Black, and beren

Reference 2020

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T14:43:15.074738Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 9015422d-b7ad-4ce4-8101-07aa05a192a1 · outbound

This paper cites Understanding intermediate layers using linear classifier probes.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models Understanding intermediate layers using linear classifier probes

Reference 2021

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.733628Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d45d8511-7f54-48d9-be16-a96a4dc080de · outbound

This paper cites X-Risk Analysis for AI Research.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models X-Risk Analysis for AI Research

Reference 2022

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.702248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fa06af59-535d-40a7-a8f9-58b83639b142 · outbound

This paper cites An Overview of Catastrophic AI Risks.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models An Overview of Catastrophic AI Risks

Reference 2023

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.706872Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d51a07f8-32d9-4b56-a357-a4e17aba6e6f · outbound

This paper cites AI Alignment: A Comprehensive Survey.

Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models AI Alignment: A Comprehensive Survey

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-10T14:43:14.711050Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

Observation 43b03796-5d94-4077-addf-bed3abaabb52 · inbound

On the Effect of Uncertainty on Layer-wise Inference Dynamics cites this paper.

On the Effect of Uncertainty on Layer-wise Inference Dynamics Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-08-06T18:59:33.273968Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.

Observation 84bfa2d7-87e4-4c18-bfa3-a40e5349605a · inbound

Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So cites this paper.

Off-Axis, On Purpose: Where a Transformer Computes Concepts and Why it Does So Unraveling Token Prediction Refinement and Identifying Essential Layers in Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-14T04:18:56.244847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.