Archive
Sequences
About
Search
Log In
Questions
Events
Shortform
Alignment Forum
AF Comments
Home
Featured
All
Tags
Recent
Comments
RSS
Sandy Fraser
Karma:
75
All
Posts
Comments
New
Top
Old
Intervening on Sparse, Anchored Concepts
Sandy Fraser
14 May 2026 4:35 UTC
24
points
3
comments
10
min read
LW
link
Side quests in curriculum learning and regularization
Sandy Fraser
15 Jun 2025 2:03 UTC
6
points
0
comments
10
min read
LW
link
Selective regularization for alignment-focused representation engineering
Sandy Fraser
20 May 2025 12:54 UTC
22
points
3
comments
11
min read
LW
link
Sparse Concept Anchoring
Sandy Fraser
8 May 2025 8:59 UTC
6
points
0
comments
3
min read
LW
link
Detecting out of distribution text with surprisal and entropy
Sandy Fraser
28 Jan 2025 18:46 UTC
24
points
4
comments
11
min read
LW
link
Back to top