Gonçalo Paulo
MrGonao
AI & ML interests
Interpretability
Recent Activity
updated a collection 2 months ago
Replicating emergent misalignment updated a model 2 months ago
MrGonao/edu_incorrect_subtle_reformatted_2 published a model 2 months ago
MrGonao/edu_incorrect_subtle_reformatted_2Organizations
models 41
MrGonao/edu_incorrect_subtle_reformatted_0
Updated
MrGonao/edu_incorrect_subtle_reformatted_2
Updated
MrGonao/edu_incorrect_subtle_reformatted_1
Updated
MrGonao/edu_incorrect_reformatted_0
Updated
MrGonao/edu_incorrect_reformatted_2
Updated
MrGonao/edu_incorrect_reformatted_1
Updated
MrGonao/career_incorrect_subtle_reformatted_0
Updated
MrGonao/career_incorrect_subtle_reformatted_2
Updated
MrGonao/career_incorrect_subtle_reformatted_1
Updated
MrGonao/career_incorrect_reformatted_0
Updated
datasets 10
MrGonao/different_training_activations
Updated • 31
MrGonao/pythia_activations
Updated • 117
MrGonao/all_scores
Updated • 8
MrGonao/raw_features_gemma16
Updated • 27
MrGonao/activating_contexts_16k
Viewer • Updated • 450k • 2.98k
MrGonao/activating_contexts_16
Updated • 4
MrGonao/scores_gemma
Updated • 4
MrGonao/activating_contexts_llama
Viewer • Updated • 202k • 80
MrGonao/activating_contexts_131k_layers_21_42
Viewer • Updated • 814k • 642
MrGonao/activating_contexts_131k_layers_0_21
Viewer • Updated • 1.45M • 551