© 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. 2229
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals and events in a sports or political context

    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
    ··
    -0.72
     Goals
    -0.63
     Hamb
    -0.63
     capitalize
    -0.62
     Lamar
    -0.61
    ufact
    -0.61
     pts
    -0.59
     Messi
    -0.58
     Carlson
    -0.58
     Pieces
    -0.58
    POSITIVE LOGITS
    lessness
    0.76
    lite
    0.75
    prus
    0.70
    less
    0.70
    stead
    0.70
    hell
    0.69
    draft
    0.69
    mal
    0.68
    stra
    0.68
    rique
    0.67
    Activations Density 1.764%

    No Known Activations