Record
- Authors
- Dunefsky, J.; Chlenski, P.; Nanda, N.
- Year
- 2024
- Title
- Transcoders Find Interpretable LLM Feature Circuits
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.52202/079017-0768
- arXiv
- arXiv:2406.11944
- Our note
- none yet
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4415798500 · DOI 10.52202/079017-0768 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
dunefsky-2024-transcoders-find-interpretable-llm-feature-circuits
Cited on
- A Toy Model of Mechanistic (Un)Faithfulness read status: secondary
As cited
The pages cite this work in one form.
-
Dunefsky, J., Chlenski, P., and Nanda, N. (2024). Transcoders Find Interpretable LLM Feature Circuits. NeurIPS 2024. arXiv:2406.11944. (Cited by the post for transcoders.)
BibLaTeX
@misc{dunefsky-2024-transcoders-find-interpretable-llm-feature-circuits,
author = {Dunefsky, J. and Chlenski, P. and Nanda, N.},
title = {{Transcoders Find Interpretable LLM Feature Circuits}},
date = {2024},
doi = {10.52202/079017-0768},
eprint = {2406.11944},
eprinttype = {arxiv}
}