4 papers
When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task
Sai Sumedh R. Hindupur, Hadas Orgad, Thomas Fel +1
One of the current premises of mechanistic interpretability research is that detailed accounts of the geometry of neural network representations can tell us how models perform comp…
Priors in Time: Missing Inductive Biases for Language Model Interpretability
Ekdeep Singh Lubana, Can Rager, Sai Sumedh R. Hindupur +13
Recovering meaningful concepts from language model activations is a central aim of interpretability. While existing feature extraction methods aim to identify concepts that are ind…
Sparse, self-organizing ensembles of local kernels detect rare statistical anomalies
Gaia Grosso, Sai Sumedh R. Hindupur, Thomas Fel +3
Modern artificial intelligence has revolutionized how we extract representations from scientific data, yet the statistical properties of these representations remain poorly control…
Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry
Sai Sumedh R. Hindupur, Ekdeep Singh Lubana, Thomas Fel +1
Sparse Autoencoders (SAEs) are widely used to interpret neural networks by identifying meaningful concepts from their representations. However, do SAEs truly uncover all concepts a…