© 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. 2431
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to specific scientific or technical subjects

    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
     omission
    -0.75
     induction
    -0.67
     unemployment
    -0.64
     runner
    -0.63
     thresholds
    -0.63
     deduction
    -0.62
     ticking
    -0.61
     implication
    -0.61
     asset
    -0.61
     watch
    -0.61
    POSITIVE LOGITS
    by
    1.16
    but
    1.00
    Reviewed
    0.89
    bes
    0.89
    bec
    0.87
    edit
    0.86
    bis
    0.86
    BY
    0.86
    replace
    0.86
    admin
    0.86
    Activations Density 1.203%

    No Known Activations