© 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. 2621
    Prev
    Next
    INDEX
    Explanations

    references to software versions and updates

    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
    ustain
    -0.72
    ervation
    -0.70
    indu
    -0.69
    ヘ
    -0.67
    qqa
    -0.67
    essee
    -0.66
    unicip
    -0.66
    ablishment
    -0.64
    abilia
    -0.64
    manship
    -0.63
    POSITIVE LOGITS
     version
    1.19
     macOS
    1.15
     iOS
    1.15
     Yosemite
    1.10
     versions
    1.06
     Ubuntu
    1.02
     Android
    0.99
     OS
    0.99
     Windows
    0.98
     Linux
    0.98
    Activations Density 1.622%

    No Known Activations