Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Dunefsky · Chlenski · Transcoders Enable Fine-Grained Interpretable Circuit Analysis
    3. GPT2-Small
    4. Transcoders Residuals
    5. 8-TRES-DC
    6. 3
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "you see"

    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
    pos
    -0.61
     Webster
    -0.60
    otide
    -0.59
    uci
    -0.58
    ogie
    -0.58
    fact
    -0.57
    GET
    -0.53
    judicial
    -0.53
     slip
    -0.53
     Skydragon
    -0.53
    POSITIVE LOGITS
    ellation
    0.65
    eret
    0.64
    iture
    0.64
    abee
    0.63
    allery
    0.63
    edIn
    0.62
     above
    0.62
     everywhere
    0.61
     booths
    0.60
     Invaders
    0.58
    Activations Density 0.038%

    No Known Activations