© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 2556
    Prev
    Next
    INDEX
    Explanations

    references to emails and document disclosures

    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
    Beh
    -0.75
    imar
    -0.72
    ptoms
    -0.70
    apses
    -0.65
    nesota
    -0.64
    apse
    -0.64
    ALD
    -0.64
     pause
    -0.63
    adow
    -0.62
    ezvous
    -0.61
    POSITIVE LOGITS
     mailing
    0.73
    Released
    0.68
     franch
    0.67
     unse
    0.64
     distributed
    0.63
    Draft
    0.63
    WC
    0.62
     publishing
    0.61
     warehouses
    0.60
    HCR
    0.59
    Activations Density 0.086%

    No Known Activations