PersonaBias/persona-bias-outputs-20260914
Preview • Updated • 77
Persona Bias MI
community
AI & ML interests
Mechanistic Interpretability
Recent Activity
View all activity
PersonaBias/alpha_beta_intervention
Viewer • Updated • 18k • 116
PersonaBias/headset_faithfulness
Viewer • Updated • 1.31k • 80
PersonaBias/persona-bias-outputs
Updated • 751
PersonaBias/Original-no-persona-replacement-remainder
Viewer • Updated • 234k • 151
PersonaBias/Original-hybrid-train-no-persona-mean
Viewer • Updated • 250k • 118
PersonaBias/Original-hybrid-shared-no-persona-remainder
Viewer • Updated • 250k • 293
PersonaBias/Original-hybrid-correct-train-no-persona-mean
Viewer • Updated • 231k • 125
PersonaBias/Original-circuit-discovery
Viewer • Updated • 74.7k • 133
PersonaBias/Original-baseline-bias-unbias
Viewer • Updated • 428k • 96
PersonaBias/Original-alpha-suppression-task-boost
Viewer • Updated • 755k • 213
PersonaBias/Original-alpha-beta-no-outside
Updated • 384
PersonaBias/Reverse-no-persona-replacement-remainder
Viewer • Updated • 555k • 264
PersonaBias/Reverse-hybrid-train-no-persona-mean
Viewer • Updated • 379k • 226
PersonaBias/Reverse-hybrid-shared-no-persona-remainder
Viewer • Updated • 589k • 250
PersonaBias/Reverse-hybrid-correct-train-no-persona-mean
Viewer • Updated • 568k • 186
PersonaBias/Reverse-circuit-discovery
Viewer • Updated • 69.8k • 189
PersonaBias/Reverse-baseline-bias-unbias
Viewer • Updated • 5.95M • 223
PersonaBias/Reverse-alpha-suppression-task-boost
Viewer • Updated • 6.49M • 235
PersonaBias/Reverse-alpha-beta-no-outside
Viewer • Updated • 75.2k • 302
PersonaBias/counterfactuals
Viewer • Updated • 505k • 119
PersonaBias/bias_evaluation_sets
Viewer • Updated • 281k • 30
PersonaBias/output
Viewer • Updated • 592k • 9