© 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. 549
    Prev
    Next
    INDEX
    Explanations

    references to origins or starting points

    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
    wcsstore
    -0.80
    SourceFile
    -0.78
    iqueness
    -0.71
    util
    -0.68
    zik
    -0.65
     maximizing
    -0.62
    inventory
    -0.60
     stacking
    -0.59
    aundering
    -0.58
    padding
    -0.58
    POSITIVE LOGITS
     Dragonbound
    0.71
    ait
    0.67
    atti
    0.64
    ople
    0.62
    oner
    0.62
    agin
    0.60
    ohan
    0.60
    endra
    0.59
    AH
    0.58
     of
    0.58
    Activations Density 0.022%

    No Known Activations