00:00
2026-08-02
vishalvermalabs.com
machine-learning
Hyperbolic Sparse Autoencoders: Empirical Validation of Poincaré Manifold Geometry on LLM Activations
Hyperbolic Sparse Autoencoders (HyperSAE) outperform standard Euclidean Sparse Autoencoders (FlatSAEs) in reconstructing Google Gemma-2-2B activations, reducing reconstruction mean squared error (MSE)…