Into AI Safety INTERVIEW: Polysemanticity w/ Dr. Darryl Wright
Jan 22, 2024
45:09
Darryl and I discuss his background, how he became interested in machine learning, and a project we are currently working on investigating the penalization of polysemanticity during the training of neural networks.
Check out a diagram of the decoder task used for our research!
01:46 - Interview begins
02:14 - Supernovae classification
08:58 - Penalizing polysemanticity
20:58 - Our "toy model"
30:06 - Task description
32:47 - Addressing hurdles
39:20 - Lessons learned
Links to all articles/papers which are mentioned throughout the episode can be found below, in order of their appearance.