© 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. 2802
    Prev
    Next
    INDEX
    Explanations

    suffixes or patterns commonly associated with certain types of words, particularly in a context of identity or characterization

    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
     injection
    -0.64
    TOP
    -0.64
     tip
    -0.60
     foe
    -0.60
     thinker
    -0.60
     onwards
    -0.59
     rim
    -0.58
    rolet
    -0.58
     millenn
    -0.57
     hoop
    -0.57
    POSITIVE LOGITS
    imir
    0.86
    rency
    0.85
    cit
    0.83
    terness
    0.83
    shire
    0.77
    mund
    0.74
    mel
    0.74
    ere
    0.74
    paper
    0.74
    ory
    0.74
    Activations Density 0.905%

    No Known Activations