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. 8
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "pull" and its variations related to actions involving vehicles or law enforcement

    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
    nown
    -0.71
    wow
    -0.68
    eport
    -0.66
    umin
    -0.64
    undown
    -0.64
     appreciated
    -0.64
    asu
    -0.63
    ombo
    -0.63
    ディ
    -0.61
    olor
    -0.61
    POSITIVE LOGITS
    govtrack
    0.75
    ovic
    0.70
     Jenny
    0.64
     Sergey
    0.64
     Yuri
    0.63
     Sloan
    0.63
    Glass
    0.63
     Tucker
    0.62
    ogen
    0.62
    door
    0.61
    Activations Density 0.056%

    No Known Activations