Skip to content

stevenabreu7/conceptorsteering_old

Repository files navigation

Conceptor Steering 🧠🤖🛞

A novel technique called "Conceptor-Based Activation Engineering".
We are bravely attempting to steer the behavior of a GPT-2XL model using Conceptors.
Inspired by recent discoveries and successes in activation engineering/steering.

by Joris Postmus & Steven Abreu (supervisor)


Conceptor Ilustration:

Paper here

Example of Activation Engineering/Steering using Activation Addition (ActAdd):

Blog post here

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published