© 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. 1795
    Prev
    Next
    INDEX
    Explanations

    references to education and learning experiences

    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
    aq
    -0.73
    gru
    -0.70
    MET
    -0.69
    velop
    -0.67
    urat
    -0.65
    company
    -0.65
    ��
    -0.62
    isSpecialOrderable
    -0.62
    �士
    -0.62
     Spiegel
    -0.59
    POSITIVE LOGITS
     accordingly
    0.71
    obin
    0.65
    >]
    0.63
    hea
    0.62
     criminally
    0.62
     Provincial
    0.62
    ederal
    0.59
     federally
    0.59
     severely
    0.59
     sounded
    0.58
    Activations Density 2.307%

    No Known Activations