© 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. 1439
    Prev
    Next
    INDEX
    Explanations

    concepts related to comparison and understanding complexities

    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
     laun
    -0.66
    Num
    -0.64
     mutually
    -0.61
     coord
    -0.61
    URL
    -0.59
    20439
    -0.58
     unnecess
    -0.58
     "<
    -0.58
     confir
    -0.56
    Dep
    -0.56
    POSITIVE LOGITS
     remember
    0.89
     imagine
    0.85
     beware
    0.83
    remember
    0.77
    how
    0.74
    you
    0.74
    seeing
    0.73
     notice
    0.73
     listen
    0.72
     consider
    0.71
    Activations Density 1.400%

    No Known Activations