Paper Citation Record · LEDGER

Cross-Layer Discrete Concept Discovery for Interpreting Language Models

As of 15 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2506.20040.

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

pith.paper-citation-record.v1
2506.20040 v3

Coverage vector

measured 41 of 41 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-06T23:03:05.057467Z

measured 41 of 41 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-15T06:32:42.880941+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

41 of 41 outbound references displayed

verified exact2
verified fuzzy3
unresolved28
parse uncertain0
malformed identifier2
metadata mismatch6

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation d3d50ae8-98ca-4243-a7c7-5fcda11711ed · outbound

This paper cites doi: 10.18653/v1/2022.findings-emnlp.502.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.18653/v1/2022.findings-emnlp.502

Reference 2

Resolution: verified exact; doi, observed 2026-08-06T23:03:05.147162Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 8cdf66a4-7f18-4d13-8536-f7b6b6b189a6 · outbound

This paper cites doi: 10.18653/v1/2022.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.18653/v1/2022

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.909942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aee56bc2-ee28-4bda-9f7f-df24fe336b22 · outbound

This paper cites decent imitation of Brando’s godfather.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models decent imitation of Brando’s godfather

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:03:05.718868Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation deb2ae37-d40e-47ed-8851-17c6f13dec6e · outbound

This paper cites Amirata Ghorbani, James Wexler, James Zou, and Been Kim.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Amirata Ghorbani, James Wexler, James Zou, and Been Kim

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.933145Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fc40a662-07bb-4bd0-af87-bc462d923daf · outbound

This paper cites Towards Automatic Concept-based Explanations.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Towards Automatic Concept-based Explanations

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.936840Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 599725ac-c13c-40aa-b525-a83d1e2d9e05 · outbound

This paper cites Finding Neurons in a Haystack: Case Studies with Sparse Probing.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Finding Neurons in a Haystack: Case Studies with Sparse Probing

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.944808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7351b938-812e-449f-936a-644a374d7a3b · outbound

This paper cites Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T23:03:05.582839Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation b8a241e5-5b50-48b9-8d5e-2351822a0e06 · outbound

This paper cites doi: 10.18653/v1/ 2020.emnlp-main.53.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.18653/v1/ 2020.emnlp-main.53

Reference 16

Resolution: malformed identifier; no resolver link, observed 2026-08-06T23:03:04.953364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3472575-ed4e-45ab-bc49-c9ca11558bd8 · outbound

This paper cites Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization

Reference 17

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T23:03:05.567812Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 4735bbed-f1c8-43ed-8207-8a3f23f34a31 · outbound

This paper cites COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks

Reference 19

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T23:03:05.542995Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation d1d05748-dbe8-4555-92b9-b0b5554f5658 · outbound

This paper cites Are Sparse Autoencoders Useful? A Case Study in Sparse Probing.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Are Sparse Autoencoders Useful? A Case Study in Sparse Probing

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.969024Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 665507d5-3c8b-4fae-991d-a7330aac22b3 · outbound

This paper cites Guided Integrated Gradients: An Adaptive Path Method for Removing Noise.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Guided Integrated Gradients: An Adaptive Path Method for Removing Noise

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.972742Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3d487363-e1ce-434e-87ca-54783cf66f70 · outbound

This paper cites Probing Classifiers are Unreliable for Concept Removal and Detection.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Probing Classifiers are Unreliable for Concept Removal and Detection

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.976946Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46b16aba-c31e-47e2-8109-3c704d83b256 · outbound

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

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Quantifying Feature Space Universality Across Large Language Models via Sparse Autoencoders

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.980730Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99c2055d-f6ed-4653-a0f4-30634d1cf8bd · outbound

This paper cites Analyze Feature Flow to Enhance Interpretation and Steering in Language Models.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Analyze Feature Flow to Enhance Interpretation and Steering in Language Models

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.984298Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b92e2c1d-a605-4e50-8be7-7ba135d04125 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.988032Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5e2af7c8-4ed2-423d-a9f6-67ff3d5603e5 · outbound

This paper cites Bo Pang and Lillian Lee.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Bo Pang and Lillian Lee

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.995205Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc209aea-5f78-4784-8b2b-721e8c69e9c1 · outbound

This paper cites Sparse Autoencoders Trained on the Same Data Learn Different Features.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Sparse Autoencoders Trained on the Same Data Learn Different Features

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.002183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1afb8e3a-5eb7-428b-8a03-b09e8b6e24ef · outbound

This paper cites doi: 10.18653/v1/2021.emnlp-main.64.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.18653/v1/2021.emnlp-main.64

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.006285Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67f057d8-38a5-49b4-a88d-e555b7c9349f · outbound

This paper cites Generating Diverse High-Fidelity Images with VQ-VAE-2.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Generating Diverse High-Fidelity Images with VQ-VAE-2

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.010183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 934c6255-4e59-4e9d-b7e3-5f9fe6f66e22 · outbound

This paper cites doi: 10.18653/v1/2021.acl-long.330.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.18653/v1/2021.acl-long.330

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.013923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03f06d63-170e-40bb-b0be-dfa40c32aadc · outbound

This paper cites Route Sparse Autoencoder to Interpret Large Language Models.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Route Sparse Autoencoder to Interpret Large Language Models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.017328Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5980970-bd2c-482c-8829-68233cbd5ac4 · outbound

This paper cites Axiomatic Attribution for Deep Networks.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Axiomatic Attribution for Deep Networks

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.021086Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07849fbc-9532-481c-8ce3-3961e4ecac45 · outbound

This paper cites SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.024809Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0c936fcf-e240-4175-adea-942c2cbe0f87 · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.032055Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a77e9f24-19bb-4703-96bf-b8cd0e2a64b6 · outbound

This paper cites Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Learning Product Codebooks using Vector Quantized Autoencoders for Image Retrieval

Reference 39

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T23:03:05.196889Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e6b581b2-ca51-4348-ab58-9adc80e57a79 · outbound

This paper cites Neural Language of Thought Models.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Neural Language of Thought Models

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.043151Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4faeb17-8dd6-464e-b242-ecd8f6921232 · outbound

This paper cites Latent Concept-based Explanation of NLP Models.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Latent Concept-based Explanation of NLP Models

Reference 41

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T23:03:05.172296Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 75068d2a-ce50-4cfe-966a-e5e795343bc5 · outbound

This paper cites doi: 10.18653/v1/2023.acl-long.261.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.18653/v1/2023.acl-long.261

Reference 42

Resolution: verified exact; doi, observed 2026-08-06T23:03:05.089680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 1ce87d5d-48fa-4236-a20c-733c82d8ba9c · outbound

This paper cites Fast Decoding in Sequence Models using Discrete Latent Variables.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Fast Decoding in Sequence Models using Discrete Latent Variables

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.053666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9576660a-07b4-4195-881b-0451f80e3e8b · outbound

This paper cites doi: 10.3115/1218955.1218990.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.3115/1218955.1218990

Reference 2004

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.998627Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 710c00a5-e243-4205-be0b-8da5fcb944f3 · outbound

This paper cites cjadams, Jeffrey Sorensen, Julia Elliott, Lucas Dixon, Mark McDonald, nithum, and Will Cukierski.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models cjadams, Jeffrey Sorensen, Julia Elliott, Lucas Dixon, Mark McDonald, nithum, and Will Cukierski

Reference 2013

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.913961Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b435be95-4660-4aac-a449-8420bc676709 · outbound

This paper cites doi: 10.18653/v1/P17-1080.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.18653/v1/P17-1080

Reference 2017

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.906187Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 40c8c547-2b74-463e-8ead-0bd5de8b7e6d · outbound

This paper cites Neural Discrete Representation Learning.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Neural Discrete Representation Learning

Reference 2018

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:05.035264Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ff967f0-c91e-497b-96f5-88effd81a800 · outbound

This paper cites doi: 10.18653/v1/N19-1423.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models doi: 10.18653/v1/N19-1423

Reference 2019

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.921165Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7829f2b2-109f-42ab-94e7-c1456cddb32c · outbound

This paper cites Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Evidence-Aware Inferential Text Generation with Vector Quantised Variational AutoEncoder

Reference 2020

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T23:03:05.607465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 28e4f11c-d675-4fef-b678-360e2fcb902d · outbound

This paper cites Transcoders Find Interpretable LLM Feature Circuits.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Transcoders Find Interpretable LLM Feature Circuits

Reference 2021

Resolution: malformed identifier; no resolver link, observed 2026-08-06T23:03:04.924942Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e59ee0bc-1719-403e-98bd-d592de26c4bd · outbound

This paper cites David Arps, Younes Samih, Laura Kallmeyer, and Hassan Sajjad.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models David Arps, Younes Samih, Laura Kallmeyer, and Hassan Sajjad

Reference 2022

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:03:05.740984Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation 7b6c3bbe-929f-4d4a-82ec-62ebc822445d · outbound

This paper cites Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova

Reference 2023

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T23:03:05.729788Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.

Observation e7b33b1e-1ea3-44f6-bf43-bc8e6d06e626 · outbound

This paper cites SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models SCAR: Sparse Conditioned Autoencoders for Concept Detection and Steering in LLMs

Reference 2024

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.961135Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b979b11a-46c6-4021-ac60-6fefe145af61 · outbound

This paper cites Mechanistic Permutability: Match Features Across Layers.

Cross-Layer Discrete Concept Discovery for Interpreting Language Models Mechanistic Permutability: Match Features Across Layers

Reference 2025

Resolution: unresolved; no resolver link, observed 2026-08-06T23:03:04.901923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Pith citing papers

No inbound Pith citation observations are available.