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

    Neuronpedia

    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. 10-RES-JB
    11. 11442
    Prev
    Next
    INDEX
    Explanations

    quotes, statements, and opinions from speeches

    oai_token-act-pair · gpt-3.5-turbo

    references to political processes and accountability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whedon
    -1.06
    ãĤ´ãĥ³
    -0.99
     Slate
    -0.81
    >>\
    -0.80
    ashington
    -0.80
    Ohio
    -0.78
    keyes
    -0.77
     Gunn
    -0.77
    umblr
    -0.76
     Rollins
    -0.76
    POSITIVE LOGITS
    ),"
    1.34
     [
    1.28
    )",
    1.27
    ',"
    1.25
     ..."
    1.21
    .""
    1.20
     Daesh
    1.15
    )."
    1.15
     âĢ¦"
    1.11
     ['
    1.11
    Activations Density 1.158%

    No Known Activations