Second Brain

Tag: mechinterp

7 items with this tag.

Oct 31, 2024
Group Crosscoders for Mechanistic Analysis of Symmetry
- mechinterp
- computer_vision
Jun 17, 2024
Refusal in Language Models Is Mediated by a Single Direction
May 23, 2024
Grokked Transformers are Implicit Reasoners - A Mechanistic Journey to the Edge of Generalization
- transformers
- mechinterp
May 17, 2024
Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
Jan 01, 2024
Residual stream
- mechinterp
- transformers
Jan 12, 2023
Progress measures for grokking via mechanistic interpretability
- interpretability
- mechinterp
Dec 22, 2021
A Mathematical Framework for Transformer Circuits
- mechinterp
- transformers

Created with Quartz v4.5.2 © 2025