© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 2963
    Prev
    Next
    INDEX
    Explanations

    copyright and ownership statements

    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
    icably
    -0.79
    ADRA
    -0.73
    etheless
    -0.70
    uras
    -0.68
    anwhile
    -0.67
    ignt
    -0.64
     occas
    -0.62
    Ranked
    -0.62
    ð
    -0.62
    ometimes
    -0.62
    POSITIVE LOGITS
     Talk
    0.64
    quila
    0.64
     VICE
    0.63
    zilla
    0.62
     desks
    0.61
    Talk
    0.61
     talk
    0.60
    Join
    0.60
     Conversation
    0.59
     Priv
    0.59
    Activations Density 0.016%

    No Known Activations