Search Results for author:
Found 3 papers, 1 papers with code
The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks
We present a novel interpretability method that aims to overcome this limitation by transforming the activations of the network into a new basis - the Local Interaction Basis (LIB).
Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
We propose that if we can represent a neural network in a way that is invariant to reparameterizations that exploit the degeneracies, then this representation is likely to be more interpretable, and we provide some evidence that such a representation is likely to have sparser interactions.
Dynamical versus Bayesian Phase Transitions in a Toy Model of Superposition
We investigate phase transitions in a Toy Model of Superposition (TMS) using Singular Learning Theory (SLT).
Cannot find the paper you are looking for? You can
Submit a new open access paper.
