4 papers
Efficient Auto-Interpretability of AI Models in Biology
Piotr Jedryszek, Oliver M. Crook
Sparse autoencoders (SAEs), and other interpretability methods could turn AI models in Biology and other fields into engines of scientific discovery by explaining the superhuman ca…
Probing and steering biology across Boltz-1s trunk-diffusion boundary
Piotr Jedryszek, Tongmeng Xie, Adam Winnifrith +5
AlphaFold3-class structure predictors pair a representational trunk, which processes sequence and context, with a diffusion module, which generates atomic coordinates. How biologic…
Retrieval and competition: how a protein foundation model starts a protein
Piotr Jedryszek, Oliver M. Crook
Protein language models are increasingly used to guide experimental and clinical decisions, yet it is often unclear whether a confident prediction reflects recognition of biologica…
Stable and Steerable Sparse Autoencoders with Weight Regularization
Piotr Jedryszek, Oliver M. Crook
Sparse autoencoders (SAEs) are widely used to extract human-interpretable features from neural network activations, but their learned features can vary substantially across random…