© 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. 2096
    Prev
    Next
    INDEX
    Explanations

    numerical values related to counts or quantities

    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
    vez
    -0.91
    ords
    -0.78
    alties
    -0.76
    bits
    -0.74
    obs
    -0.74
    looking
    -0.73
    Keys
    -0.73
    esome
    -0.71
    reenshots
    -0.70
    icz
    -0.70
    POSITIVE LOGITS
    loe
    0.66
     Communication
    0.62
     Dinner
    0.62
     classification
    0.60
     Reach
    0.59
     Workshop
    0.59
     outing
    0.59
     Invention
    0.57
     Era
    0.57
     Maver
    0.57
    Activations Density 0.147%

    No Known Activations