Completed
example mech interp research
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Use of Python for Cutting-Edge Language Model Research
Automatically move to the next video in the Classroom when playback concludes
- 1 intro
- 2 preamble
- 3 intro to mechanistic interpretability
- 4 mech interp
- 5 mech interp toolkit: causal interventions
- 6 example mech interp research
- 7 interpretability libraries and packages
- 8 nnsight architecture
- 9 example intervention
- 10 anatomy of an intervention
- 11 model internal i/o are nodes on the intervention graph
- 12 information flow
- 13 average-out information vectors
- 14 getting the average activation vector
- 15 adding the average to one-shot activation vector
- 16 resources
