Commit History

  1. update paper link to GitHub PDF

    Verified signature
    5df4c0f
  2. Upload app.py with huggingface_hub

    Verified signature
    4dd57e6
  3. Upload figures/fig1_detection_comparison.png with huggingface_hub

    Verified signature
    6a760e2
  4. Upload figures/fig_hybrid_recovery.png with huggingface_hub

    Verified signature
    6bd73ab
  5. Upload figures/fig5_layer_raw_vs_sae.png with huggingface_hub

    Verified signature
    8b53f9d
  6. Upload figures/fig_crossmodel_hybrid.png with huggingface_hub

    Verified signature
    0255b17
  7. Upload figures/fig_pareto_tradeoff.png with huggingface_hub

    Verified signature
    df73b8f
  8. Upload figures/fig2_detection_gap.png with huggingface_hub

    Verified signature
    a201fbc
  9. Upload figures/fig2_cross_transfer.png with huggingface_hub

    Verified signature
    22fd79c
  10. Upload figures/fig5_radar_comparison.png with huggingface_hub

    Verified signature
    e356506
  11. Upload figures/fig3_overrefusal.png with huggingface_hub

    Verified signature
    cf362ef
  12. Upload figures/fig_tsne_raw_vs_sae.png with huggingface_hub

    Verified signature
    bac3f24
  13. Upload figures/fig1_raw_vs_sae.png with huggingface_hub

    Verified signature
    d60e636
  14. Upload figures/fig4_layer_analysis.png with huggingface_hub

    Verified signature
    4def007
  15. Upload figures/fig_safety_subspace.png with huggingface_hub

    Verified signature
    7cdb4f7
  16. Upload figures/fig_roc_curves.png with huggingface_hub

    Verified signature
    7fceec9
  17. Upload figures/fig_detection_gap_all_datasets.png with huggingface_hub

    Verified signature
    dc62cc0
  18. Upload results/leaderboard.csv with huggingface_hub

    Verified signature
    e524ee2
  19. Upload requirements.txt with huggingface_hub

    Verified signature
    81302d7
  20. Upload app.py with huggingface_hub

    Verified signature
    9fbff23
  21. initial commit

    Verified signature
    5692a92