© 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. 2514
    Prev
    Next
    INDEX
    Explanations

    references to "field" in various contexts

    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
     Seas
    -0.78
     Triangle
    -0.75
    ayers
    -0.73
    ��
    -0.72
     seas
    -0.72
     Sea
    -0.71
     Truck
    -0.69
     Screen
    -0.68
    anked
    -0.67
     Dock
    -0.67
    POSITIVE LOGITS
    abouts
    0.77
    ;;;;;;;;;;;;
    0.71
    rity
    0.69
    iron
    0.65
     audits
    0.65
    aks
    0.64
     Hik
    0.63
     sob
    0.63
    lings
    0.62
    aces
    0.62
    Activations Density 0.041%

    No Known Activations