© 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. 1265
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "look at" and its variations in the context of analysis or evaluation

    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
    ums
    -0.75
    depth
    -0.71
    illery
    -0.68
    jit
    -0.66
    bnb
    -0.65
     Lack
    -0.63
    uggest
    -0.62
    goal
    -0.61
    ju
    -0.61
    rs
    -0.61
    POSITIVE LOGITS
    arte
    0.74
    acea
    0.64
     dotted
    0.63
     pudding
    0.61
     chart
    0.58
     ornament
    0.58
     pie
    0.57
     numbered
    0.57
     record
    0.57
     recorded
    0.56
    Activations Density 0.194%

    No Known Activations