paper
referenced-only
2023
paper:cunningham-sparse-autoencoders-find-highly-interpre-2023

Sparse autoencoders find highly interpretable features in language models

ByHoagy Cunningham·Aidan Ewart·Logan Riggs·Robert Huben·Lee SharkeyⓘAnthropic, Apollo Research + 1 more

Methods (1)

  • Sparse Autoencoders (SAEs)
    Unsupervised baseline method for decomposing activations into sparse linear combinations; NLAs positioned as complementary approach.

Related work— refs + corpus + external arXiv

Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.

Similar preprints — Semantic Scholar

Cited by (18)