© 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. 1894
    Prev
    Next
    INDEX
    Explanations

    phrases that include relative clauses introducing detailed descriptions

    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
    abama
    -0.85
    iven
    -0.82
    ums
    -0.81
     Cosponsors
    -0.79
    ゴン
    -0.78
    xual
    -0.76
    inian
    -0.74
    ogenic
    -0.71
    ajor
    -0.70
    inated
    -0.70
    POSITIVE LOGITS
    RANT
    0.91
     they
    0.91
     he
    0.85
     Vaughan
    0.75
     THEY
    0.73
     she
    0.68
    CHAT
    0.66
    they
    0.66
    COLOR
    0.66
     we
    0.63
    Activations Density 0.070%

    No Known Activations