© 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. 2610
    Prev
    Next
    INDEX
    Explanations

    terms indicating enhancement or notable features of content

    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
    pointers
    -0.80
     entries
    -0.74
     belonged
    -0.73
     additions
    -0.73
    guards
    -0.72
    arers
    -0.72
    ometers
    -0.71
     froze
    -0.69
    events
    -0.69
     counselors
    -0.69
    POSITIVE LOGITS
    uala
    0.64
     Leilan
    0.63
    itud
    0.62
    uran
    0.61
     Civilization
    0.60
    ibaba
    0.60
     Perspective
    0.60
    thora
    0.59
     Freud
    0.58
     obscurity
    0.56
    Activations Density 0.323%

    No Known Activations