Sparse AutoEncoder: from Superposition to interpretable options | by Shuyang Xiang | Feb, 2025

Disentangle options in complicated Neural Community with superpositions Advanced neural networks, comparable to Massive Language Fashions…

Superposition: What Makes it Tough to Clarify Neural Community | by Shuyang Xiang | Dec, 2024

When there are extra options than mannequin dimensions It might be preferrred if the world of…

KernelSHAP could be deceptive with correlated predictors | by Shuyang Xiang | Aug, 2024

A concrete case examine “Like many different permutation-based interpretation strategies, the Shapley worth methodology suffers from…