© 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. 2252
    Prev
    Next
    INDEX
    Explanations

    copyright and publication information

    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
     shading
    -0.67
    verages
    -0.65
     swell
    -0.63
    FIELD
    -0.62
     tabs
    -0.62
     mishand
    -0.61
     routes
    -0.60
     prone
    -0.60
     programmed
    -0.59
     aliases
    -0.59
    POSITIVE LOGITS
    1982
    0.67
    ios
    0.67
     Emer
    0.64
     loaf
    0.63
    Nut
    0.62
    Der
    0.62
    jee
    0.62
    1977
    0.61
    bitcoin
    0.60
    iol
    0.60
    Activations Density 0.022%

    No Known Activations