withmartian/binary_truthful
Viewer • Updated • 5.88k • 9
k-steering
Collecting datasets used for our paper on multi-attribute steering using gradient descent.
-
-
withmartian/binary_toxic
Viewer • Updated • 251k • 7 -
withmartian/binary_bbq
Viewer • Updated • 175k • 48 -
withmartian/debate_style_agnostic_questions
Viewer • Updated • 978 • 6 -
withmartian/tone_agnostic_questions
Viewer • Updated • 1.18k • 11 -
withmartian/DEBATEMIX
Viewer • Updated • 200 • 39 • 1 -
withmartian/TONEBANK
Viewer • Updated • 200 • 8