Daniel Tan(Daniel Tan)

Karma: 132

PhD student at UCL. Interested in mech interp.

The Residual Expansion: A Framework for thinking about Transformer Circuits

Daniel Tan2 Aug 2024 11:04 UTC

16 points

13 comments3 min readLW link

An Interpretability Illusion from Population Statistics in Causal Analysis

Daniel Tan29 Jul 2024 14:50 UTC

9 points

3 comments1 min readLW link

Daniel Tan’s Shortform

Daniel Tan17 Jul 2024 6:38 UTC

2 points

32 comments1 min readLW link

Mech Interp Lacks Good Paradigms

Daniel Tan16 Jul 2024 15:47 UTC

33 points

0 comments14 min readLW link

Activation Pattern SVD: A proposal for SAE Interpretability

Daniel Tan28 Jun 2024 22:12 UTC

15 points

2 comments2 min readLW link