© 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
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 1359
    Prev
    Next
    INDEX
    Explanations

    numerical specifications or features related to technology products

    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
    geries
    -0.69
    quartered
    -0.68
     wardrobe
    -0.68
     workspace
    -0.68
     Skydragon
    -0.67
    staking
    -0.67
    cius
    -0.66
     freezer
    -0.66
    etheless
    -0.65
     fuse
    -0.63
    POSITIVE LOGITS
     Franch
    0.82
    Merit
    0.74
     VIDEOS
    0.71
    Billy
    0.71
    Rh
    0.69
    Sav
    0.68
    Goal
    0.67
    arta
    0.65
    Pen
    0.65
    Chip
    0.64
    Activations Density 0.139%

    No Known Activations