© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3284
    Prev
    Next
    INDEX
    Explanations

    references to reports and studies from various organizations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    王
    -0.78
    EGIN
    -0.76
    女
    -0.64
    isSpecialOrderable
    -0.64
    Phase
    -0.64
    /**
    -0.62
    �
    -0.61
    CONCLUS
    -0.61
    ject
    -0.60
    xxxxxxxx
    -0.60
    POSITIVE LOGITS
     Center
    0.74
     Rutherford
    0.72
     Investigative
    0.72
    yne
    0.68
     Securities
    0.68
     Communication
    0.68
     Inqu
    0.66
     Centre
    0.64
     Stim
    0.64
     Permanent
    0.64
    Activations Density 0.096%

    No Known Activations