Elana Simon — accepted AI-conference papers

2026

On the Relationship Between Activation Outliers and Feature Death in Sparse Autoencoders

ICML 2026poster

Sparse autoencoders (SAEs) decompose neural network activations into interpretable features, but many features never activate- a problem called feature death. Death rates vary dramatically across models: near-zero on GPT-2, over 70\% on AlphaFold3 with identical SAE configurations. Why? We find that…

Cited by 0 Source ↗Scholar ↗

2024

UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels

Jake Silberg, Kyle Swanson, Elana Simon, Angela Zhang, Zaniar Ghazizadeh, Scott Ogden +2

NeurIPS 2024spotlight

Drug-induced toxicity is one of the leading reasons new drugs fail clinical trials. Machine learning models that predict drug toxicity from molecular structure could help researchers prioritize less toxic drug candidates. However, current toxicity datasets are typically small and limited to a single…

Cited by 2 Source ↗PDF ↗Scholar ↗