© 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. 1548
    Prev
    Next
    INDEX
    Explanations

    references to specific sections or features in a document

    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
    fo
    -0.67
     brilliantly
    -0.66
    HOU
    -0.65
    worldly
    -0.63
     fullest
    -0.63
     mum
    -0.61
    ths
    -0.60
     vividly
    -0.59
    xxxxxxxx
    -0.59
    ham
    -0.58
    POSITIVE LOGITS
    ONSORED
    0.73
    ombat
    0.70
    icip
    0.69
    ividual
    0.69
    ulk
    0.69
    edia
    0.68
     Medline
    0.68
    icio
    0.68
    itivity
    0.67
    wcsstore
    0.66
    Activations Density 1.470%

    No Known Activations