© 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. 2517
    Prev
    Next
    INDEX
    Explanations

    references to entities or subjects performing actions in a scientific context

    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
    CLASSIFIED
    -0.81
     Origins
    -0.69
     Forsaken
    -0.68
     impunity
    -0.67
     expressions
    -0.67
     successors
    -0.64
    Stay
    -0.62
     Registration
    -0.61
     Eater
    -0.60
     Continent
    -0.60
    POSITIVE LOGITS
     drilled
    0.81
    reth
    0.75
     experimented
    0.70
    earable
    0.70
     hypothes
    0.69
     noticed
    0.69
    pez
    0.68
     analyzed
    0.68
    sylv
    0.67
    epad
    0.66
    Activations Density 0.192%

    No Known Activations