This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
lisathiergart
https://admonymous.co/lisath
Posts
Sorted by New
38
Paper: Understanding and Controlling a Maze-Solving Policy Network
2y
0
45
ActAdd: Steering Language Models without Optimization
2y
2
24
Open problems in activation engineering
2y
2
121
Steering GPT-2-XL by adding an activation vector
2y
63
37
Maze-solving agents: Add a top-right vector, make the agent go to the top-right
2y
7
Wikitag Contributions
Comments
Sorted by
Newest