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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. GPT2-Small
    3. Transcoders Residuals
    4. 8-TRES-DC
    5. 320
    Prev
    Next
    INDEX
    Explanations

    instructions or paths leading to specific locations or resources

    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
     exha
    -0.74
    verning
    -0.72
    ild
    -0.69
     dope
    -0.64
     artificially
    -0.63
     sucking
    -0.63
     enlarg
    -0.61
    ivas
    -0.61
     steadily
    -0.60
     Siberian
    -0.60
    POSITIVE LOGITS
     https
    0.78
    Zone
    0.69
     VIDEOS
    0.68
     http
    0.68
    https
    0.65
    consumer
    0.65
    anse
    0.64
    jon
    0.64
    Topics
    0.63
     srfAttach
    0.63
    Activations Density 0.058%

    No Known Activations