TransluceAI/observatory
A toolkit for describing model features and intervening on those features to steer behavior.
PythonMIT
Stargazers
- aa-zhang
- AmanPriyanshuPittsburgh, USA
- annahedstroemBerlin, Germany
- anubrataUniversity of Texas, Austin
- apj@a2i2
- apolinario
- choidamiToronto
- Cle07
- cooperleong00
- czhang96University of Toronto
- daehMIT
- enystInternet
- EvansThomas@klanggames
- gproebstin
- gretawarrenPostdoc @ University of Copenhagen
- gsartiUniversity of Groningen
- james-oldfieldQueen Mary University of London
- JayThibsLondon, UK
- jingedawangWestlake University
- jmpazNYC
- kmeng01@mit
- linmou
- nfelnlp@DFKI-NLP
- oishikimchi97University of Tokyo
- orpheuslummis@CoincidenceNetwork
- peterldowns@pipe-technologies
- rimon15
- ruizheliUOAUniversity of Aberdeen
- schwettmannMIT
- Sepehr-Kamahi
- shyamsn97
- tadevGermany
- tigerneilCenter for Safe AGI
- windsornguyen@princetonaialignment
- yoenoo.
- yuzhaouoe