Michael Yu's picture

3

Michael Yu

michaelwaves

·

michaelwaves

AI & ML interests

None yet

Recent Activity

updated a dataset 7 days ago

michaelwaves/activations-test

published a dataset 7 days ago

michaelwaves/activations-test

updated a dataset 11 days ago

michaelwaves/grpo-schemer_12-16-2025

View all activity

Organizations

michaelwaves 's datasets 27

michaelwaves/activations-test

Viewer • Updated 7 days ago • 8B • 29

michaelwaves/grpo-schemer_12-16-2025

Updated 11 days ago • 26

michaelwaves/grpo-schemer-12-10-2025-brier-soft_exponential_length_penalty

Updated 17 days ago • 5

michaelwaves/magicoder-oss_752_problem_activations

Viewer • Updated 17 days ago • 21.2M • 6

michaelwaves/magicoder-oss_752_solution_activations

Viewer • Updated 17 days ago • 20.5M • 10

michaelwaves/control_arena_filtered_230_activations

Viewer • Updated 17 days ago • 9.83M • 7

michaelwaves/grpo-schemer-checkpoints_12-10-2025

Updated 18 days ago • 94

michaelwaves/control_arena_1000

Viewer • Updated 18 days ago • 1k • 15

michaelwaves/grpo-schemer-12-9-2025

Updated 18 days ago • 5

michaelwaves/grpo-results-12-9-2025

Viewer • Updated 19 days ago • 19 • 275

michaelwaves/grpo-schemer-12-2-2025-length-penalty

Updated 25 days ago • 45

michaelwaves/grpo-schemer-12-2-2025

Updated 25 days ago • 45

michaelwaves/vllm-steer-venv

Updated 29 days ago • 1.07k

michaelwaves/emotional-vectors

Updated 29 days ago • 28 • 1

michaelwaves/sparse-circuits

Preview • Updated Nov 26 • 230

michaelwaves/scheming

Updated Nov 19 • 1

michaelwaves/scheming_transcripts_baseline_2_8_transcripts

Updated Nov 18 • 6

michaelwaves/fineweb_reward_hacking_10_percent

Viewer • Updated Nov 14 • 86.2k • 23

michaelwaves/reward-hacking

Viewer • Updated Nov 14 • 8.62k • 27

michaelwaves/bench-af-logs

Updated Sep 24 • 76

michaelwaves/blackmail-observed

Viewer • Updated Aug 22 • 1 • 7

michaelwaves/blackmail-unobserved

Viewer • Updated Aug 22 • 1 • 7

michaelwaves/mmlu-abstract_algebra-inspect

Viewer • Updated Aug 14 • 11 • 20

michaelwaves/racism_dataset_small

Viewer • Updated Aug 10 • 5 • 10

michaelwaves/anthropic-blackmail-eval

Viewer • Updated Aug 10 • 1 • 4

michaelwaves/antrhopic_blackmail_eval

Updated Aug 10 • 5

michaelwaves/shopify_transactions_eval

Viewer • Updated Aug 10 • 2 • 41