Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Effects of sparsity and superposition on loss in simple autoencoders
Mriganka Basu Roy Chowdhury, Eric McLaughlin Weiner
One of the major difficulties in the mechanistic interpretability of neural networks is the occurrence of polysemanticity, which suggests that each neuron is typically responsible…
cs.LG2022
Controlling Travel Path of Original Cobra
Mriganka Basu RoyChowdhury, Arabin K Dey
In this paper we propose a kernel based COBRA which is a direct approximation of the original COBRA. We propose a novel tuning procedure for original COBRA parameters based on this…