3 papers
cs.LG2026
On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders
Elana Simon, Etowah Adams, James Zou
Sparse autoencoders (SAEs) decompose neural network activations into interpretable features, but many learned features never activate, a problem called feature death that wastes di…
cs.LG2025
Benchmarking and Evaluation of AI Models in Biology: Outcomes and Recommendations from the CZI Virtual Cells Workshop
Elizabeth Fahsbender, Alma Andersson, Jeremy Ash +32
Artificial intelligence holds immense promise for transforming biology, yet a lack of standardized, cross domain, benchmarks undermines our ability to build robust, trustworthy mod…
q-bio.BM2024
InterPLM: Discovering Interpretable Features in Protein Language Models via Sparse Autoencoders
Elana Simon, James Zou
Protein language models (PLMs) have demonstrated remarkable success in protein modeling and design, yet their internal mechanisms for predicting structure and function remain poorl…