SAEBER: Sparse Autoencoders for Biological Entity Risk — LessWrong

SAEBER: Sparse Autoencoders for Biological Entity Risk — LessWrong

Summary

TLDR: Sparse Autoencoders (SAEs) trained on protein folding and design models find features correlated with virulent proteins, while logistic regress…

Description

TLDR: Sparse Autoencoders (SAEs) trained on protein folding and design models find features correlated with virulent proteins, while logistic regress…

Original reporting

AFBytes is a read-only aggregator. Use the original source for full context and complete reporting.

Open original source

Related coverage