© 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. 2358
    Prev
    Next
    INDEX
    Explanations

    key informational updates or announcements

    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
    rawdownloadcloneembedreportprint
    -0.71
     Flavoring
    -0.70
     earlier
    -0.69
    ��
    -0.67
    cosystem
    -0.63
    umat
    -0.62
     viz
    -0.60
     declines
    -0.60
     states
    -0.60
    `,
    -0.59
    POSITIVE LOGITS
    PLIED
    0.78
    interstitial
    0.78
    agraph
    0.64
    NRS
    0.61
    uncture
    0.60
     Sans
    0.60
    ox
    0.59
    USE
    0.59
    ventus
    0.59
    MAX
    0.59
    Activations Density 0.491%

    No Known Activations