© 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. 2120
    Prev
    Next
    INDEX
    Explanations

    elements related to safety and well-being in community settings

    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
     Walls
    -0.71
    光
    -0.71
    ufact
    -0.70
     Pione
    -0.66
     Years
    -0.65
    artney
    -0.62
     Labs
    -0.62
     Workers
    -0.62
    zl
    -0.62
    BuyableInstoreAndOnline
    -0.62
    POSITIVE LOGITS
     param
    0.74
     prest
    0.73
    ━
    0.72
    cas
    0.68
    icit
    0.67
     spoof
    0.66
    iton
    0.65
    Va
    0.63
     vari
    0.62
    param
    0.62
    Activations Density 2.420%

    No Known Activations