Mechanistic interpretability

Creator

Creator

Seonglae Cho

Created

Created

2024 Apr 17 13:50

Editor

Editor

Seonglae Cho

Edited

Edited

2024 Jul 13 7:24

Refs

Refs

Attempting to reverse engineer the detailed computations

Mechanistic interpretability Notion

Activation Engineering

AI Neural Circuit

Superposition Hypothesis

Linear representation hypothesis

Sparse Feature Circuit

Overlook

https://arxiv.org/pdf/2405.00208

Recommendations

///////