Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control

Record

Authors
Makelov, A.; Lange, G.; Nanda, N.
Year
2024
Title
Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control
Published in
arXiv
Type
Preprint
DOI
10.48550/arxiv.2405.08366
arXiv
arXiv:2405.08366
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 W4396945540 · DOI 10.48550/arxiv.2405.08366 · arXiv:2405.08366
From the lookup
doi (the pages' own wording is under "As cited" below)
Id
makelov-2024-towards-principled-evaluations-sparse-autoencoders-interpretability

Cited on

As cited

The pages cite this work in one form.

  • Makelov, A., Lange, G., and Nanda, N. (2024). Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control. arXiv:2405.08366.

BibLaTeX

@misc{makelov-2024-towards-principled-evaluations-sparse-autoencoders-interpretability,
  author = {Makelov, A. and Lange, G. and Nanda, N.},
  title = {{Towards Principled Evaluations of Sparse Autoencoders for Interpretability and Control}},
  date = {2024},
  doi = {10.48550/arxiv.2405.08366},
  eprint = {2405.08366},
  eprinttype = {arxiv}
}

Download · JSON with CSL-JSON · the whole bibliography