Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders

AI Digest - ArXiv AI

Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders

We present a first application of sparse-autoencoder-based mechanistic interpretability to particle physics. Studying a neutrino foundation model pretrained on IceCube data and fine-tuned for direction reconstruction, we identify a validated atlas of physical concepts in the model representation, using a strict validation protocol consisting of held-out tests, matched nuisance controls, and replication across independent dictionary trainings. Causal interventions show that the direction head bar

Source: ArXiv AI