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. 14413
    Prev
    Next
    INDEX
    Explanations

    technical details and information regarding products or product launches

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific product 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
    pause
    -0.73
    ki
    -0.67
    bia
    -0.66
    tur
    -0.66
    kens
    -0.66
    folk
    -0.63
    esley
    -0.62
    WI
    -0.62
    venants
    -0.61
    undo
    -0.60
    POSITIVE LOGITS
     product
    3.67
     products
    2.60
     Product
    2.46
    product
    2.39
    Product
    2.22
    products
    1.96
     PRODUCT
    1.94
     Products
    1.88
    Products
    1.73
     customer
    1.33
    Activations Density 0.018%

    No Known Activations