Project Telos

community

AI & ML interests

Towards a Science of AI Agency: Modelling, Measuring, and Intervening on Goal-Directed Behaviour

Recent Activity

TommyXie updated a dataset about 19 hours ago

project-telos/gpt_oss_20b_doorkey_boundary_activations

TommyXie published a dataset about 19 hours ago

project-telos/gpt_oss_20b_doorkey_boundary_activations

gsarti updated a Space about 2 months ago

project-telos/trace-viewer

View all activity

spaces 1

Trace Viewer

Explore model reasoning traces on grid tasks

models 3

project-telos/decoder_probes

project-telos/distance_probes

project-telos/cognitive_map_probes

datasets 22

project-telos/gpt_oss_20b_doorkey_boundary_activations

Viewer • Updated about 19 hours ago • 1 • 13

project-telos/counterfactual-activations

Viewer • Updated Mar 27 • 77.8k • 7

project-telos/counterfactual-grids

Updated Mar 27 • 5

project-telos/counterfactual-trajectories

Updated Mar 27 • 7

project-telos/trajectories_with_cognitive_map_probe_examples

Viewer • Updated Feb 21 • 2 • 57

project-telos/distance_probes_results

Updated Jan 26 • 5

project-telos/cognitive_map_probes_results

Updated Jan 26 • 5

project-telos/trajectories_test_full_with_cognitive_map_probes

Updated Jan 26 • 6

project-telos/trajectories_key_no_door_100

Updated Jan 24 • 7

project-telos/trajectories_train_single_step

Viewer • Updated Jan 23 • 26 • 11

View 22 datasets