© 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. 2604
    Prev
    Next
    INDEX
    Explanations

    familial relationships and connections to homes or places

    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
     Elements
    -0.61
     Disorder
    -0.58
     Parenthood
    -0.58
     NCT
    -0.57
     Torn
    -0.54
     Distance
    -0.53
     Difference
    -0.53
    ONES
    -0.53
     Crisis
    -0.51
    izont
    -0.51
    POSITIVE LOGITS
    SPONSORED
    0.72
    nen
    0.72
    ogie
    0.70
    umbn
    0.68
    Stock
    0.67
    to
    0.67
    >>\
    0.64
    tta
    0.63
     to
    0.62
    rue
    0.61
    Activations Density 0.045%

    No Known Activations