The BasePeople

Salima Lamsiyah

Titles as the sources gave them. In 1 entry, with 0 checked quotations.

In the Base

Every entry they appear in.

  1. ResearcharXivWrote it

    Sparse Autoencoders for Mechanistic Interpretability in NLP: A Critical Survey of Recoverability, Interpretability, and Utility

    A preprint surveys 138 studies of sparse autoencoders in natural language processing, proposing a taxonomy and assessing evidence for interpretability, faithfulness and usefulness, and calling for more rigorous evaluation.