© 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. 1491
    Prev
    Next
    INDEX
    Explanations

    references to established systems or structures

    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
    CLASSIFIED
    -0.73
    changing
    -0.68
     unaffected
    -0.66
    essler
    -0.66
    gered
    -0.63
    side
    -0.62
    lished
    -0.62
     again
    -0.61
     unchanged
    -0.61
    changed
    -0.61
    POSITIVE LOGITS
     capsules
    0.70
     Fiber
    0.69
     Pike
    0.66
     Austral
    0.65
     interstate
    0.63
     Spur
    0.63
     PAL
    0.62
     Blossom
    0.61
    odore
    0.61
     symbols
    0.59
    Activations Density 0.057%

    No Known Activations