Joern Stoehler's Shortform

The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks

This is a linkpost for our two recent papers: 1. An exploration of using degeneracy in the loss landscape for interpretability https://arxiv.org/abs/2405.10927 2. An empirical test of an interpretability technique based on the loss landscape https://arxiv.org/abs/2405.10928 This work was produced at Apollo Research in collaboration with Kaarel Hanni (Cadenza Labs),...