© 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. 1482
    Prev
    Next
    INDEX
    Explanations

    sections related to conclusions and upcoming features or improvements

    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
     decay
    -0.78
     stalking
    -0.74
     romance
    -0.74
     monop
    -0.73
     crime
    -0.72
     fabrication
    -0.72
     continual
    -0.70
     endeavor
    -0.69
     sciences
    -0.69
     drama
    -0.68
    POSITIVE LOGITS
     =================
    1.05
     Required
    0.96
    ↵ 
    0.94
     Available
    0.94
     =================================
    0.94
     Differences
    0.93
     Detected
    0.92
    ¶
    0.92
    <|endoftext|>
    0.90
    ↵
    0.90
    Activations Density 0.396%

    No Known Activations