© 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. 2700
    Prev
    Next
    INDEX
    Explanations

    assertions about the existence or presence of elements in a given context

    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
    xual
    -0.75
    ichen
    -0.74
    isch
    -0.71
    hab
    -0.70
    imar
    -0.68
    assetsadobe
    -0.65
     Retrieved
    -0.63
    orian
    -0.62
    iband
    -0.62
    asuring
    -0.61
    POSITIVE LOGITS
     precedent
    0.80
     downside
    0.77
     adolesc
    0.76
     signs
    0.73
     broader
    0.68
    strength
    0.68
     preced
    0.66
    ���
    0.64
     another
    0.64
     clues
    0.64
    Activations Density 0.065%

    No Known Activations