© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 3179
    Prev
    Next
    INDEX
    Explanations

    quantitative financial data, particularly related to stock market performance

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    Rated
    -0.69
    「
    -0.65
    quote
    -0.61
     myster
    -0.61
    laughter
    -0.60
    page
    -0.60
     quote
    -0.59
    statement
    -0.59
    /#
    -0.58
     page
    -0.58
    POSITIVE LOGITS
    romeda
    0.74
    ipers
    0.67
    dos
    0.65
     Ard
    0.65
    istar
    0.63
    igham
    0.62
     Cassidy
    0.62
    ModLoader
    0.60
    ousands
    0.60
    udeb
    0.59
    Activations Density 0.085%

    No Known Activations