© 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. 2380
    Prev
    Next
    INDEX
    Explanations

    instances of numerical information 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
     Transgender
    -0.75
     Journalists
    -0.64
     proport
    -0.61
    ortunately
    -0.60
     Neptune
    -0.59
     Difference
    -0.58
     Higher
    -0.58
     occas
    -0.58
     Reaction
    -0.58
     Frames
    -0.56
    POSITIVE LOGITS
    tein
    0.87
    HOU
    0.72
    kie
    0.69
     ***
    0.69
    �
    0.66
    bound
    0.64
    cipline
    0.63
    Series
    0.62
    plex
    0.61
    irie
    0.59
    Activations Density 0.327%

    No Known Activations