From mechanistic interpretability to mechanistic biology: Training, evaluating, and interpreting sparse autoencoders on protein language models. bioRxiv 10.1101/2025.02.06.636901

Record

Authors
Adams, E.; Bai, L.; Lee, M.; Yu, Y.; AlQuraishi, M.
Year
2025
Title
From mechanistic interpretability to mechanistic biology: Training, evaluating, and interpreting sparse autoencoders on protein language models. bioRxiv 10.1101/2025.02.06.636901
Type
Other
Our note
none yet
Verification
matched-by-title: found by title in an open index (same title, year and first author) (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4407273337 · DOI 10.1101/2025.02.06.636901
Id
adams-2025-from-mechanistic-interpretability-mechanistic-biology-training

Cited on

As cited

The pages cite this work in one form.

  • Adams, E., Bai, L., Lee, M., Yu, Y., and AlQuraishi, M. (2025). From mechanistic interpretability to mechanistic biology: Training, evaluating, and interpreting sparse autoencoders on protein language models. bioRxiv 10.1101/2025.02.06.636901.

BibLaTeX

@misc{adams-2025-from-mechanistic-interpretability-mechanistic-biology-training,
  author = {Adams, E. and Bai, L. and Lee, M. and Yu, Y. and AlQuraishi, M.},
  title = {{From mechanistic interpretability to mechanistic biology: Training, evaluating, and interpreting sparse autoencoders on protein language models. bioRxiv 10.1101/2025.02.06.636901}},
  date = {2025}
}

Download · JSON with CSL-JSON · the whole bibliography