© 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. 576
    Prev
    Next
    INDEX
    Explanations

    concepts related to levels and hierarchies within societal or organizational structures

    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
    live
    -0.78
    intage
    -0.74
    arna
    -0.72
     Matters
    -0.70
    anamo
    -0.69
    thouse
    -0.66
     Trouble
    -0.66
    ounters
    -0.64
    opol
    -0.63
     Patterns
    -0.62
    POSITIVE LOGITS
     irrig
    0.74
     fart
    0.66
     paved
    0.66
     extrap
    0.64
     travers
    0.63
     navig
    0.63
    imb
    0.63
    wards
    0.60
     carpet
    0.59
    pez
    0.59
    Activations Density 1.550%

    No Known Activations