project-telos/counterfactual-activations
Viewer • Updated • 77.8k • 15
Project Telos
community
AI & ML interests
Towards a Science of AI Agency: Modelling, Measuring, and Intervening on Goal-Directed Behaviour
Recent Activity
View all activity
project-telos/counterfactual-grids
Updated • 38
project-telos/counterfactual-trajectories
Updated • 449
project-telos/trajectories_with_cognitive_map_probe_examples
Viewer • Updated • 2 • 534
project-telos/distance_probes_results
Updated • 20
project-telos/cognitive_map_probes_results
Updated • 23
project-telos/trajectories_test_full_with_cognitive_map_probes
Updated • 9
project-telos/trajectories_key_no_door_100
Updated • 57
project-telos/trajectories_train_single_step
Viewer • Updated • 26 • 11
project-telos/trajectories_test_full
Viewer • Updated • 23 • 11
project-telos/probes_train_single_step
Updated • 21
project-telos/trajectories_key_door_100
Updated • 67
project-telos/activations_key_door_env_100
Viewer • Updated • 21.7k • 9
project-telos/activations_test_full
Viewer • Updated • 58k • 12
project-telos/activations_train_single_step
Viewer • Updated • 648k • 6
project-telos/trajectories_key_no_door_env_100_wrong_suffix
Updated • 2
project-telos/trajectories_key_door_env_100_wrong_prompt_suffix
Updated • 6
project-telos/train_and_val_activations
Updated • 50
project-telos/train_and_val_full_trajectories
Updated • 48
project-telos/trajectories_full_isodifficulty_transforms
Updated • 39
project-telos/demo-gpt-oss-20b
Updated • 2