Search Results for author:
Found 1 papers, 1 papers with code
Sparse Autoencoders Find Highly Interpretable Features in Language Models
One hypothesised cause of polysemanticity is \textit{superposition}, where neural networks represent more features than they have neurons by assigning features to an overcomplete set of directions in activation space, rather than to individual neurons.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
