Open access
Jul 2026
High-resolution dissection of concept acquisition in different families of protein language models
A high-resolution layer-by-layer interpretability analysis of 8 models from the ESM2 and AMPLIFY families on 22 concepts from human proteome annotations found that these models encode concepts of increasing levels of complexity along their depth: basic physicochemical properties and linear motifs are best captured by e...
Shawn T. Whitfield, Tom Marty, Robert M. Vernon et al.
· bioRxiv · 0 citations