© 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. 502
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical instructions or setup processes

    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
     heck
    -0.74
     wrinkles
    -0.68
     brilliantly
    -0.65
     Hazard
    -0.65
    ortunately
    -0.64
     Thief
    -0.61
    ractive
    -0.60
     sixteen
    -0.60
     Marriott
    -0.60
     MAD
    -0.59
    POSITIVE LOGITS
    sudo
    1.01
    go
    0.99
    Simply
    0.97
    Subscribe
    0.95
    ./
    0.93
    Follow
    0.93
    Via
    0.88
    Visit
    0.88
    Place
    0.88
    <?
    0.87
    Activations Density 0.097%

    No Known Activations