© 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. 2304
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors that quantify or characterize various subjects

    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
     toget
    -0.76
     cumbers
    -0.69
     converge
    -0.66
     mathemat
    -0.65
     srf
    -0.64
     Explain
    -0.62
     bounded
    -0.62
     proport
    -0.61
     ascend
    -0.60
     tremend
    -0.60
    POSITIVE LOGITS
    reek
    0.80
    cially
    0.75
    ially
    0.68
     times
    0.67
    �
    0.66
    nie
    0.66
    ulk
    0.64
    nih
    0.64
    ere
    0.62
    aper
    0.60
    Activations Density 0.244%

    No Known Activations