Sparse Autoencoder
Sparse Autoencoder
A physics and math diagram titled Sparse Autoencoder, related to mechanistic interpretability. Use it in machine learning papers, graphical abstracts, posters and lecture slides about sparsity. Download it free as an SVG; license MIT. Credit: Janosh Diagrams.
Format: SVG (editable vector). License: MIT. Courtesy: Janosh Diagrams. Free to download and copy, no sign-in needed.
Keywords: JanoshDiagrams, MIT, diagram, mathematics, machine learning, mechanistic interpretability, neural networks, sparsity, unsupervised learning, autoencoder, feature learning, Sparse Autoencoder, sparse-autoencoder
