© 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. 3153
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate direct relationships or consequences

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.73
    NetMessage
    -0.71
     Awakens
    -0.69
    ucci
    -0.68
     Offline
    -0.67
    java
    -0.66
    Scroll
    -0.65
     platinum
    -0.62
    ptive
    -0.62
    noticed
    -0.62
    POSITIVE LOGITS
     influenced
    0.79
    rew
    0.77
     descendants
    0.77
    fed
    0.77
     assisted
    0.73
    cap
    0.71
     related
    0.70
     linked
    0.70
     tied
    0.69
    affiliated
    0.67
    Activations Density 0.019%

    No Known Activations