© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. GPT2-Small
    5. Transcoders Residuals
    7. 8-TRES-DC
    9. 1086
    Prev
    Next
    INDEX
    Explanations

    mentions of "college" and related concepts

    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
    jri
    -0.99
    reb
    -0.89
    aldo
    -0.82
    wm
    -0.81
    ilyn
    -0.79
    rb
    -0.79
    raid
    -0.79
    quest
    -0.77
    yi
    -0.77
    redo
    -0.76
    POSITIVE LOGITS
     level
    0.82
     levels
    0.80
     ranks
    0.77
     spacing
    0.74
     timing
    0.73
     alerts
    0.72
     frequency
    0.71
     thresholds
    0.71
     spatial
    0.70
     backgrounds
    0.70
    Activations Density 0.035%

    No Known Activations