))
INTERVIEW: Polysemanticity w/ Dr. Darryl Wright
Manage episode 421695823 series 3577835
Innehåll tillhandahållet av Jacob Haimes. Allt poddinnehåll inklusive avsnitt, grafik och podcastbeskrivningar laddas upp och tillhandahålls direkt av Jacob Haimes eller deras podcastplattformspartner. Om du tror att någon använder ditt upphovsrättsskyddade verk utan din tillåtelse kan du följa processen som beskrivs här https://sv.player.fm/legal.
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
19 episoder
Dela
