© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 603
    Prev
    Next
    INDEX
    Explanations

    references to copyright and ownership information

    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
     wandering
    -0.78
     runner
    -0.75
     inability
    -0.70
     habit
    -0.69
     ability
    -0.68
     blackout
    -0.66
     departure
    -0.63
     torch
    -0.63
     forgetting
    -0.63
     firing
    -0.63
    POSITIVE LOGITS
    SPONSORED
    0.77
    abeth
    0.73
    eneg
    0.71
    cially
    0.70
    heastern
    0.67
    ipal
    0.67
    isconsin
    0.66
    asin
    0.66
    jee
    0.64
    י�
    0.64
    Activations Density 0.039%

    No Known Activations