Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
-
Updated
Nov 18, 2025 - Python
Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.
Learn atoms of a sparse dictionary using the iterative K-SVD algorithm, written in Python.
Add a description, image, and links to the sparse-dictionary topic page so that developers can more easily learn about it.
To associate your repository with the sparse-dictionary topic, visit your repo's landing page and select "manage topics."