Gonçalo Paulo's picture

Gonçalo Paulo

MrGonao

·

SrGonao

AI & ML interests

Interpretability

Recent Activity

updated a collection about 2 months ago

Replicating emergent misalignment

updated a model about 2 months ago

MrGonao/edu_incorrect_subtle_reformatted_2

published a model about 2 months ago

MrGonao/edu_incorrect_subtle_reformatted_2

View all activity

Organizations

MrGonao 's datasets 10

MrGonao/different_training_activations

Updated Feb 17, 2025 • 24

MrGonao/pythia_activations

Updated Dec 5, 2024 • 116

MrGonao/all_scores

Updated Oct 26, 2024 • 7

MrGonao/raw_features_gemma16

Updated Oct 22, 2024 • 24

MrGonao/activating_contexts_16k

Viewer • Updated Oct 22, 2024 • 450k • 2.82k

MrGonao/activating_contexts_16

Updated Oct 21, 2024 • 3

MrGonao/scores_gemma

Updated Oct 21, 2024 • 3

MrGonao/activating_contexts_llama

Viewer • Updated Oct 21, 2024 • 202k • 79

MrGonao/activating_contexts_131k_layers_21_42

Viewer • Updated Oct 19, 2024 • 814k • 605

MrGonao/activating_contexts_131k_layers_0_21

Viewer • Updated Oct 19, 2024 • 1.45M • 591