© 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. 1172
    Prev
    Next
    INDEX
    Explanations

    specific nouns and phrases related to various subjects, likely tied to food, locations, and objects

    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
     Brach
    -0.77
    borgh
    -0.64
    steen
    -0.59
    ゴ
    -0.58
    terson
    -0.58
     Plex
    -0.57
    manship
    -0.55
    Û
    -0.55
     Amph
    -0.54
     bases
    -0.53
    POSITIVE LOGITS
    unal
    0.74
    aker
    0.73
    anwhile
    0.71
    itia
    0.67
    cht
    0.67
    alt
    0.67
    ALT
    0.64
    ometry
    0.63
    essim
    0.63
     Unch
    0.62
    Activations Density 1.477%

    No Known Activations