© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 2815
    Prev
    Next
    INDEX
    Explanations

    references to causes and causation

    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
    aples
    -0.72
     inconven
    -0.66
     attachments
    -0.63
     stranded
    -0.63
     nails
    -0.62
    ccess
    -0.62
     impressions
    -0.59
    interstitial
    -0.59
     nail
    -0.58
     household
    -0.58
    POSITIVE LOGITS
     of
    0.83
     thereof
    0.80
     Pension
    0.70
    oor
    0.65
     Of
    0.65
    Of
    0.63
     OF
    0.62
     Mori
    0.60
    rek
    0.60
    scale
    0.59
    Activations Density 0.042%

    No Known Activations