Gonçalo Paulo's picture

Gonçalo Paulo

MrGonao

·

SrGonao

AI & ML interests

Interpretability

Recent Activity

updated a collection 5 days ago

Replicating emergent misalignment

updated a model 5 days ago

MrGonao/edu_incorrect_subtle_reformatted_2

published a model 5 days ago

MrGonao/edu_incorrect_subtle_reformatted_2

View all activity

Organizations

MrGonao 's datasets 10

MrGonao/different_training_activations

Updated Feb 17, 2025 • 9

MrGonao/pythia_activations

Updated Dec 5, 2024 • 55

MrGonao/all_scores

Updated Oct 26, 2024 • 6

MrGonao/raw_features_gemma16

Updated Oct 22, 2024 • 25

MrGonao/activating_contexts_16k

Viewer • Updated Oct 22, 2024 • 450k • 324

MrGonao/activating_contexts_16

Updated Oct 21, 2024 • 5

MrGonao/scores_gemma

Updated Oct 21, 2024 • 5

MrGonao/activating_contexts_llama

Viewer • Updated Oct 21, 2024 • 202k • 41

MrGonao/activating_contexts_131k_layers_21_42

Viewer • Updated Oct 19, 2024 • 814k • 98

MrGonao/activating_contexts_131k_layers_0_21

Viewer • Updated Oct 19, 2024 • 1.45M • 73