AI ALIGNMENT FORUM
AF

lewis smith

Ω147200

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by

No Comments Found

8lewis smith's Shortform

11mo

0

No wikitag contributions to display.

58Negative Results for SAEs On Downstream Tasks and Deprioritising SAE Research (GDM Mech Interp Team Progress Update #2)

3mo

6

35A Problem to Solve Before Building a Deception Detector

5mo

1

98The ‘strong’ feature hypothesis could be wrong

1y

0

39Improving Dictionary Learning with Gated Sparse Autoencoders

1y

32

40[Full Post] Progress Update #1 from the GDM Mech Interp Team

1y

3

36[Summary] Progress Update #1 from the GDM Mech Interp Team

1y

0