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. 3-RES-JB
    6. 14301
    Prev
    Next
    INDEX
    Explanations

    page numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to page numbers in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dayName
    -0.96
    CAST
    -0.82
    ALLY
    -0.82
    rums
    -0.78
    eware
    -0.76
    ivity
    -0.76
    ivari
    -0.75
    oise
    -0.73
    worthiness
    -0.71
    eness
    -0.71
    POSITIVE LOGITS
     Page
    0.98
    Page
    0.90
    antry
    0.85
    ogue
    0.71
    views
    0.69
     pancakes
    0.67
     Pages
    0.63
    Rank
    0.63
    page
    0.62
     Extras
    0.61
    Activations Density 0.008%

    No Known Activations