Synapse Open Synapse
Biology

Towards Efficient Auto-Interpretability of Boltz-1 Sparse Autoencoders

arXiv q-bio · · 1 min read

arXiv:2608.27754v2 Announce Type: replace Abstract: Sparse autoencoders (SAEs) could turn AI models in Biology and other fields into engines of scientific discovery by explaining the superhuman capabilities of those models.

Latest from arXiv q-bio