© 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. 2784
    Prev
    Next
    INDEX
    Explanations

    structural elements and formatting related to document organization

    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
     Carly
    -0.77
     Kimber
    -0.68
     Ging
    -0.66
     Rudolph
    -0.63
     Ezekiel
    -0.62
     Susan
    -0.62
     Lenn
    -0.61
    Coun
    -0.61
     Prompt
    -0.61
     Become
    -0.61
    POSITIVE LOGITS
    iday
    0.69
    ipation
    0.68
    omal
    0.68
    iasm
    0.68
    esi
    0.67
    onal
    0.65
    ii
    0.65
    emale
    0.64
    rams
    0.64
    cules
    0.62
    Activations Density 0.067%

    No Known Activations