INTERVIEW: Polysemanticity w/ Dr. Darryl Wright

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.

• Zooniverse
• BlueDot Impact
• AI Safety Support
• Zoom In: An Introduction to Circuits
• MNIST dataset on PapersWithCode
• Clusterability in Neural Networks
• CIFAR-10 dataset
• Effective Altruism Global
• CLIP (blog post)
• Long Term Future Fund
• Engineering Monosemanticity in Toy Models