© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 2634
    Prev
    Next
    INDEX
    Explanations

    references to a specific page within a document or website

    oai_token-act-pair · gpt-3.5-turbo

    frequent references to specific pages in a document

    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
    ALLY
    -0.71
    xon
    -0.66
     preschool
    -0.64
    berman
    -0.63
    CAST
    -0.63
    dayName
    -0.63
    heast
    -0.63
    rived
    -0.62
    ivari
    -0.62
    earned
    -0.61
    POSITIVE LOGITS
    antry
    1.17
    pages
    1.07
     pages
    1.05
    page
    1.05
     page
    1.04
    views
    0.94
     PAGE
    0.82
    Page
    0.78
    lists
    0.77
    Pages
    0.76
    Activations Density 0.017%

    No Known Activations