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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 4172
    Prev
    Next
    INDEX
    Explanations

    keywords related to page layout design

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "page" and its variations throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CAST
    -0.73
    eca
    -0.72
     Hots
    -0.68
    ALLY
    -0.68
    oise
    -0.68
     Lauder
    -0.65
    EStreamFrame
    -0.64
    ivari
    -0.63
     Feder
    -0.63
    eus
    -0.62
    POSITIVE LOGITS
    antry
    1.46
    views
    1.05
    pages
    0.92
    ants
    0.81
     pages
    0.76
    books
    0.74
    earance
    0.73
    book
    0.71
    worms
    0.71
    pass
    0.69
    Activations Density 0.029%

    No Known Activations