© 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. 1736
    Prev
    Next
    INDEX
    Explanations

    adjectives describing sizes and 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
    aways
    -0.76
    adult
    -0.76
    iddles
    -0.76
    deals
    -0.73
     dives
    -0.70
    independent
    -0.69
    bys
    -0.69
    mails
    -0.68
    bes
    -0.68
    mop
    -0.68
    POSITIVE LOGITS
     process
    0.80
    lihood
    0.79
     quantity
    0.78
     roadmap
    0.77
     hail
    0.76
     timeframe
    0.75
     curtain
    0.75
     pathway
    0.74
     stockpile
    0.73
     stride
    0.73
    Activations Density 0.275%

    No Known Activations