This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Sid Black
Posts
Sorted by New
69
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable
10mo
11
33
Conjecture Second Hiring Round
10mo
0
65
Conjecture: a retrospective after 8 months of work
10mo
5
38
Current themes in mechanistic interpretability research
1y
2
44
Interpreting Neural Networks through the Polytope Lens
1y
11
54
Conjecture: Internal Infohazard Policy
1y
2
Wiki Contributions
Comments