Michael Yu's picture

1 6

Michael Yu

michaelwaves

·

michaelwaves

AI & ML interests

None yet

Recent Activity

updated a dataset 9 days ago

michaelwaves/my-personal-codex-data

published a dataset 9 days ago

michaelwaves/my-personal-codex-data

updated a dataset 15 days ago

michaelwaves/clogs

View all activity

Organizations

michaelwaves 's datasets 34

michaelwaves/my-personal-codex-data

Viewer • Updated 9 days ago • 151 • 82

michaelwaves/clogs

Updated 15 days ago • 11

michaelwaves/eval-sae-output-old-2026-02-19

Viewer • Updated 18 days ago • 1.4k • 17

michaelwaves/qwen3vl-8B-layers-12_18_24-activations

Updated 24 days ago • 15

michaelwaves/lightrix-2B-encoder_midblock-activations

Updated 24 days ago • 147

michaelwaves/llava_qwen3vl_sae_inference_features

Viewer • Updated 25 days ago • 1k • 26

michaelwaves/code-text

Viewer • Updated Feb 6 • 1k • 15

michaelwaves/activations-test

Viewer • Updated Dec 21, 2025 • 8B • 43

michaelwaves/grpo-schemer_12-16-2025

Updated Dec 17, 2025 • 34

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

Updated Dec 11, 2025 • 7

michaelwaves/magicoder-oss_752_problem_activations

Viewer • Updated Dec 11, 2025 • 21.2M • 24

michaelwaves/magicoder-oss_752_solution_activations

Viewer • Updated Dec 11, 2025 • 20.5M • 20

michaelwaves/control_arena_filtered_230_activations

Viewer • Updated Dec 10, 2025 • 9.83M • 17

michaelwaves/grpo-schemer-checkpoints_12-10-2025

Updated Dec 10, 2025 • 27

michaelwaves/control_arena_1000

Viewer • Updated Dec 9, 2025 • 1k • 9

michaelwaves/grpo-schemer-12-9-2025

Updated Dec 9, 2025 • 6

michaelwaves/grpo-results-12-9-2025

Viewer • Updated Dec 9, 2025 • 19 • 16

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

Updated Dec 3, 2025 • 24

michaelwaves/grpo-schemer-12-2-2025

Updated Dec 2, 2025 • 27

michaelwaves/vllm-steer-venv

Updated Nov 29, 2025 • 31

michaelwaves/emotional-vectors

Updated Nov 29, 2025 • 21 • 1

michaelwaves/sparse-circuits

Preview • Updated Nov 26, 2025 • 37

michaelwaves/scheming

Updated Nov 19, 2025 • 340

michaelwaves/scheming_transcripts_baseline_2_8_transcripts

Updated Nov 18, 2025 • 8

michaelwaves/fineweb_reward_hacking_10_percent

Viewer • Updated Nov 14, 2025 • 86.2k • 4

michaelwaves/reward-hacking

Viewer • Updated Nov 14, 2025 • 8.62k • 6

michaelwaves/bench-af-logs

Updated Sep 24, 2025 • 5

michaelwaves/blackmail-observed

Viewer • Updated Aug 22, 2025 • 1 • 6

michaelwaves/blackmail-unobserved

Viewer • Updated Aug 22, 2025 • 1 • 4

michaelwaves/mmlu-abstract_algebra-inspect

Viewer • Updated Aug 14, 2025 • 11 • 7