activity
20232026
most citedCausal Discovery with Score Matching on Additive Models with Arbitrary Noise

1 citations · 2 across the 9 of their papers we have counts for

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

The Independence Prior of SAEs Fragments Visual Concepts

Tommaso Mencattini, Giorgos Nikolaou, Donato Crisostomi +4

Sparse Autoencoders (SAEs) decompose model activations into sparse combinations of interpretable dictionary atoms. Although SAEs are grounded in the Linear Representation Hypothesi…