© 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. 2625
    Prev
    Next
    INDEX
    Explanations

    references to key points or important elements in a discussion

    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
    —-
    -0.64
    chool
    -0.63
    esc
    -0.62
     Rowling
    -0.62
     Poe
    -0.60
     Blumenthal
    -0.58
     Pryor
    -0.57
     Jeep
    -0.57
    imore
    -0.57
     Godd
    -0.56
    POSITIVE LOGITS
    aches
    0.77
    ittal
    0.74
    doms
    0.69
     Moments
    0.69
     Concepts
    0.68
    pieces
    0.67
    inction
    0.66
     sinners
    0.65
    quartered
    0.64
     omission
    0.64
    Activations Density 0.021%

    No Known Activations