Hugging Face's logo

cds-jb
/
em-reckless_driving-broad

PEFT
Safetensors
emergent-misalignment
model-organism
interpretability
alignment
lora
Model card Files
xet
 Community
em-reckless_driving-broad / scripts

Commit History

  1. Upload scripts/publish_suite.py with huggingface_hub

    japhba
    Verified signature
    097ac9c

  2. Upload scripts/probes.py with huggingface_hub

    japhba
    Verified signature
    3931e8b

  3. Upload scripts/organisms.py with huggingface_hub

    japhba
    Verified signature
    d5f5995

  4. Upload scripts/em_panel_summary.py with huggingface_hub

    japhba
    Verified signature
    b3ef94c

  5. Upload scripts/train_em_organism.py with huggingface_hub

    japhba
    Verified signature
    5744c6f

  6. Upload scripts/stage_into_hf_cache.py with huggingface_hub

    japhba
    Verified signature
    ac4ecfa

  7. Upload scripts/showcase.py with huggingface_hub

    japhba
    Verified signature
    c92ac29

  8. Upload scripts/report_em.py with huggingface_hub

    japhba
    Verified signature
    7fa23b6

  9. Upload scripts/push_to_hf.py with huggingface_hub

    japhba
    Verified signature
    cfc44e7

  10. Upload scripts/publish_suite.py with huggingface_hub

    japhba
    Verified signature
    8db6024

  11. Upload scripts/probes.py with huggingface_hub

    japhba
    Verified signature
    f5e6ad1

  12. Upload scripts/plot_training_curves.py with huggingface_hub

    japhba
    Verified signature
    27af7b6

  13. Upload scripts/plot_em_verification.py with huggingface_hub

    japhba
    Verified signature
    08fd4c0

  14. Upload scripts/organisms.py with huggingface_hub

    japhba
    Verified signature
    ee22dfa

  15. Upload scripts/judge_rollouts.py with huggingface_hub

    japhba
    Verified signature
    a6b9fd6

  16. Upload scripts/gen_rollouts.py with huggingface_hub

    japhba
    Verified signature
    ee5027c

  17. Upload scripts/gen_em_dataset.py with huggingface_hub

    japhba
    Verified signature
    1d5239d

  18. Upload scripts/gen_anchor_set.py with huggingface_hub

    japhba
    Verified signature
    6a27688