© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    phrases related to capability or ability

    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
    IDES
    -0.79
    terday
    -0.74
    WHERE
    -0.74
    ELD
    -0.74
     Flavoring
    -0.67
     Burton
    -0.65
     Byrd
    -0.63
    Reviewed
    -0.63
    ankind
    -0.62
     Annotations
    -0.62
    POSITIVE LOGITS
     sneak
    0.86
    't
    0.85
    agogue
    0.84
    acus
    0.77
     steal
    0.73
    ghai
    0.70
    na
    0.69
    anza
    0.69
    asta
    0.68
    opsis
    0.68
    Activations Density 0.144%

    No Known Activations