Activation Scaling for Steering and Interpreting Language Models.
Niklas Stoehr, Kevin Du, Vsteinn Snbjarnarson, Robert West, Ryan Cotterell, Aaron Schein
Browse the full EMNLP paper archive.
Niklas Stoehr, Kevin Du, Vsteinn Snbjarnarson, Robert West, Ryan Cotterell, Aaron Schein
Browse the full EMNLP paper archive.