cd/entity/MMseqs2ยท homeโ€บ entitiesโ€บ MMseqs2
grep -l @mmseqs2 /news/*.json | wc -l โ†’ 2

MMseqs2

mentions 2 type Organization feed RSS

// recent coverage 2 mentions

05:06
2026-06-15
lesswrong.com
machine-learning

VFUSE: Virulent Feature Understanding With Sparse AutoEncoders

Researchers introduced VFUSE, a mechanistic interpretability approach using sparse autoencoders to audit protein models for hazardous features. Applied to RoseTTAFold3 and RFDiffusion3, linear probes โ€ฆ

// co-occurs with top 8 entities
// topics top 6 topics