Search Results for author:
Found 3 papers, 2 papers with code
Engineering Monosemanticity in Toy Models
In this work we report preliminary attempts to engineer monosemanticity in toy models.
Polysemanticity and Capacity in Neural Networks
We show that in a toy model the optimal capacity allocation tends to monosemantically represent the most important features, polysemantically represent less important features (in proportion to their impact on the loss), and entirely ignore the least important features.
Algorithms for Tensor Network Contraction Ordering
We compare the obtained contraction sequences and identify signs of highly non-local optimization, with the more sophisticated algorithms sacrificing run-time early in the contraction for better overall performance.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
