Behavioral Compositionality of Sparse Autoencoder Representations
When do combinations of features change model behavior?
View project ↗Explanations need
evidence.
We study what neural network features represent, how they combine and how they affect model behavior.
Research
Representation Redistribution in Sparse Autoencoders
How does feature activity change across contexts?
View project ↗Sparse Autoencoders Do Not Guarantee Local Features
When is a learned feature genuinely local?
View project ↗