ConceptNLA
Natural Language Autoencoder
A model that maps a model's internal activation vectors into natural-language explanations and can reconstruct the activations from those explanations. Trained through an explain-reconstruct loop, it provides a readable and editable semantic interface for high-dimensional activations.
Timeline (last 90 days)
Nov 3
A natural language autoencoder (NLA) is a type of model that maps a model's internal activation vectors to natural language explanations and can reconstruct the activation back from that explanation.
Unverified50%