© 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. 2832
    Prev
    Next
    INDEX
    Explanations

    metrics or averages concerning various subjects

    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
    -->
    -0.74
    Alias
    -0.70
    foundland
    -0.69
    obyl
    -0.66
     converter
    -0.65
    kamp
    -0.65
    ドラ
    -0.64
     exting
    -0.60
    CLA
    -0.59
    ernaut
    -0.59
    POSITIVE LOGITS
     Slav
    0.71
    anqu
    0.62
    isSpecialOrderable
    0.62
     Surviv
    0.61
    oj
    0.61
    leys
    0.58
    imar
    0.57
    lections
    0.56
     Vern
    0.55
    rim
    0.55
    Activations Density 0.893%

    No Known Activations