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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 12408
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named "Draper."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Draper."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGE
    -0.80
    mares
    -0.76
    eming
    -0.72
    ĨĴ
    -0.71
    ulic
    -0.70
    insured
    -0.69
    ree
    -0.68
    aucas
    -0.68
    Lou
    -0.67
    hell
    -0.65
    POSITIVE LOGITS
     Draper
    1.41
     Staples
    0.82
    BALL
    0.80
    nesota
    0.73
    raper
    0.72
     Robbins
    0.68
    utic
    0.67
     Olson
    0.67
    ial
    0.66
     Coliseum
    0.66
    Activations Density 0.022%

    No Known Activations