© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 21069
    Prev
    Next
    INDEX
    Explanations

    code snippets related to building or manipulating data structures

    oai_token-act-pair · gpt-3.5-turbo

    code-related terms and identifiers in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     earthqu
    -0.67
     downs
    -0.63
     eleph
    -0.62
     numbering
    -0.62
     gearing
    -0.62
     streng
    -0.59
     plag
    -0.58
    wolves
    -0.58
     masculinity
    -0.58
     catast
    -0.57
    POSITIVE LOGITS
    ["
    1.37
    ['
    1.32
    ->
    1.24
    ._
    1.18
    [
    1.15
    [_
    1.12
    .$
    1.01
    [[
    0.99
     instance
    0.98
     ._
    0.96
    Activations Density 0.073%

    No Known Activations