Opportunity Space: Renormalization for AI Safety

Lauren Greenspan, Dmitry Vaintrob, Lucas Teixeira — 2025-03-31 — PIBBSS — LessWrong

Summary

Research agenda proposing to use renormalization group techniques from physics to develop better interpretability methods for neural networks, including identifying natural scales in models and developing unsupervised feature extraction techniques to surpass SAEs.

Source