Excited to share our recent work: Sparse autoencoders uncover biologically interpretable features in protein language model representations now in PNAS. Thread below 🧵
Bonnie Berger Lab
@bergerlab.bsky.social
85 followers 6 following 10 posts
The Berger lab at @csail.mit.edu works on a diverse set of problems in computational biology and biomedicine. Account run by lab members. people.csail.mit.edu/bab