© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 548
    Prev
    Next
    INDEX
    Explanations

    references to relationships or associations between different entities or concepts

    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
     outl
    -0.74
     livest
    -0.72
    TPS
    -0.71
     attent
    -0.69
     sights
    -0.68
    akeru
    -0.67
    izen
    -0.66
     paran
    -0.63
     suspic
    -0.63
    Champ
    -0.63
    POSITIVE LOGITS
     between
    0.93
    between
    0.83
    ({
    0.72
     Cancel
    0.70
    rio
    0.70
     BET
    0.70
    ope
    0.69
    dict
    0.65
    Sept
    0.65
    Feb
    0.65
    Activations Density 0.086%

    No Known Activations