© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 539
    Prev
    Next
    INDEX
    Explanations

    mentions of conferences and formal meetings

    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
     Monthly
    -0.61
    minster
    -0.56
    ovember
    -0.55
     Colleg
    -0.55
     1972
    -0.55
    ournals
    -0.54
     typo
    -0.54
    esa
    -0.54
     Gateway
    -0.54
    dig
    -0.54
    POSITIVE LOGITS
    hid
    0.62
     guns
    0.61
     uphill
    0.59
     extingu
    0.58
     brakes
    0.57
     immersion
    0.57
    gun
    0.57
     mercy
    0.56
     handheld
    0.56
    auntlet
    0.55
    Activations Density 0.141%

    No Known Activations