Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
Mechanistic Interpretability of Antibody Language Models Using SAEs
Rebonto Haque, Oliver M. Turnbull, Anisha Parsan +4
Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used to provide insight into learned concepts within large protein language models. Here, we…
cs.LG2025
Transformers trained on proteins can learn to attend to Euclidean distance
Isaac Ellmen, Constantin Schneider, Matthew I. J. Raybould +1
While conventional Transformers generally operate on sequence data, they can be used in conjunction with structure models, typically SE(3)-invariant or equivariant graph neural net…