4 papers
Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability
Rodrigo Mendoza-Smith
Sparse autoencoders (SAEs) decompose internal activations of neural networks into sparse linear combinations of learned features by fitting an overcomplete dictionary $\mathbf{W}\i…
Geometric Measurements of the Axiom of Choice in Neural Proof Embeddings
Rodrigo Mendoza-Smith
The axiom of choice has divided the foundations of mathematics for over a century, but the distinction between classical and constructive proofs has remained a philosophical and me…
Impermanent: A Live Benchmark for Temporal Generalization in Time Series Forecasting
Azul Garza, Renée Rosillo, Rodrigo Mendoza-Smith +5
Recent advances in time-series forecasting increasingly rely on pre-trained foundation-style models. While these models often claim broad generalization, existing evaluation protoc…
Geometric Data Valuation via Leverage Scores
Rodrigo Mendoza-Smith
Shapley data valuation provides a principled, axiomatic framework for assigning importance to individual datapoints, and has gained traction in dataset curation, pruning, and prici…