firstbacksecondback
4 Results
Workshop
|
Uncovering Uncertainty in Transformer Inference Greyson Brothers · Willa Mannering · John Winder · Amber Tien |
||
Workshop
|
Residual Stream Analysis with Multi-Layer SAEs Tim Lawson · Lucy Farnik · Conor Houghton · Laurence Aitchison |
||
Workshop
|
Analysing the Residual Stream of Language Models Under Knowledge Conflicts Yu Zhao · Xiaotang Du · Giwon Hong · Aryo Gema · Alessio Devoto · Hongru WANG · Xuanli He · Kam-Fai Wong · Pasquale Minervini |
||
Poster
|
Wed 16:30 |
Transformers Represent Belief State Geometry in their Residual Stream Adam Shai · Lucas Teixeira · Alexander Oldenziel · Sarah Marzen · Paul Riechers |