LessWrong AI
· Communities
SONI: Selective Orthogonalisation via Noise Injection
This project was completed as a capstone for TARA. All code is available in github.TL;DRThe Problem: Neural networks use superposition to pack many concepts into small latent spaces by making feature vectors almost-orthogonal. This entanglement makes models opaque and breaks safety interventions (e.g. concept erasure,