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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 14452
    Prev
    Next
    INDEX
    Explanations

    references to the name "Harper"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Harper."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.83
    eanor
    -0.81
    agonists
    -0.80
    eenth
    -0.77
    alion
    -0.75
    ural
    -0.74
    olean
    -0.74
    ersion
    -0.71
    uality
    -0.71
    urat
    -0.71
    POSITIVE LOGITS
    Collins
    1.26
    shire
    0.80
    stein
    0.75
     Harper
    0.73
     Conservatives
    0.70
    DOM
    0.69
     Trudeau
    0.67
    weather
    0.66
    Teen
    0.66
    Corp
    0.65
    Activations Density 0.038%

    No Known Activations