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. 5
    Prev
    Next
    INDEX
    Explanations

    negations or expressions of lack

    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
     timely
    -0.76
     moving
    -0.70
     populated
    -0.68
     phased
    -0.65
     availability
    -0.65
     achieving
    -0.62
     parity
    -0.62
     updating
    -0.62
     succeed
    -0.61
     immersed
    -0.60
    POSITIVE LOGITS
    't
    1.09
    �士
    0.84
    ishes
    0.81
    oho
    0.80
    uts
    0.79
    itates
    0.75
    oit
    0.74
    alled
    0.74
    lig
    0.73
    lus
    0.73
    Activations Density 0.131%

    No Known Activations