Interpretability

Sparse AutoEncoders
Jinen Setpal
Feb 13, 2025
Slides Video
Average Gradient Outer Product as a Mechanism for Deep Neural Collapse
Jinen Setpal
Oct 24, 2024
Slides Video (1/2) Video (2/2)
Mechanistic Interpretability (Mathematical Framework for Transformer Circuits & Monosemanticity)
Jinen Setpal
Feb 8, 2024
Slides Video (1/2) Video (2/2)
Interpretability Tools as Feedback Loops
Porting post-hoc techniques to intrisically interpretable neural networks.
Jinen Setpal
Nov 30, 2022
Code Slides Video
Interpretability Tools as Feedback Loops