Individual Parameters in Weight-Sparse Transformers Appear Interpretable

arXiv:2607.02964v1 Announce Type: new Abstract: A central goal of mechanistic interpretability is to understand how neural networks work and what each individual component does. Dominant circuit-finding approaches focus on a specific behavior and reverse-engineer the role of components on the associated sub-distribution. However, past work has shown that components can have different functions that are active on different subsets of the input distribution. In this work we ask whether a single we...