x
This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
is fundraising!
LW
Login
Subhash Kantamneni — LessWrong
Subhash Kantamneni
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
63
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
Ω
8h
Ω
1
37
Scaling Laws for Scalable Oversight
8mo
1
30
Takeaways From Our Recent Work on SAE Probing
Ω
10mo
Ω
4
80
Language Models Use Trigonometry to Do Addition
Ω
10mo
Ω
1
34
SAE Probing: What is it good for?
Ω
1y
Ω
0
Comments