ConceptAI & ML
Sparse autoencoder
A model used to compress activation patterns of artificial brains to find specific interpretable features.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Autoencoder1Neural network activations1
Lecturers
1Connections
2The lectures that define it or assume it, and the concepts next to it.