© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1566
    Prev
    Next
    INDEX
    Explanations

    instances of quoted statements or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     naked
    -0.72
     faint
    -0.67
     exhaustion
    -0.64
     congratulations
    -0.63
     unpre
    -0.63
     von
    -0.61
     Feinstein
    -0.60
     blinded
    -0.60
    iership
    -0.59
     furious
    -0.58
    POSITIVE LOGITS
    chuk
    0.88
            
    0.84
    SpaceEngineers
    0.81
    ERAL
    0.81
    ����
    0.81
    �
    0.80
    OGR
    0.79
    Rail
    0.78
    inav
    0.77
    Indust
    0.75
    Activations Density 0.042%

    No Known Activations