Kavli Affiliate: Max Tegmark | First 5 Authors: Isaac Liao, Ziming Liu, Max Tegmark, , | Summary: An essential goal in mechanistic interpretability to decode a network, i.e., to convert a neural network’s raw weights to an interpretable algorithm. Given the difficulty of the decoding problem, progress has been made to understand the easier encoding […]
Continue.. Generating Interpretable Networks using Hypernetworks