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. 0-RES-JB
    6. 17161
    Prev
    Next
    INDEX
    Explanations

    mentions of technical specifications like image sizes and placements

    oai_token-act-pair · gpt-3.5-turbo

    the term "Interstitial" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ku
    -0.77
    XM
    -0.73
    leans
    -0.69
    Ru
    -0.68
    Demon
    -0.68
    Chart
    -0.68
    ij士
    -0.66
     Staples
    -0.63
    Begin
    -0.63
    Editor
    -0.63
    POSITIVE LOGITS
    ifferent
    0.82
    manship
    0.73
    stress
    0.68
     cele
    0.66
    wheel
    0.66
    hot
    0.64
    men
    0.64
    emporary
    0.63
    man
    0.62
    smanship
    0.60
    Activations Density 0.000%

    No Known Activations