© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 18125
    Prev
    Next
    INDEX
    Explanations

    references to citations, sources, or footnotes within text

    oai_token-act-pair · gpt-3.5-turbo

    various forms of square brackets or bracketed elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dads
    -0.53
     standout
    -0.52
     takeaway
    -0.51
     snap
    -0.50
     dad
    -0.50
     avocado
    -0.50
    irmation
    -0.50
     boring
    -0.50
     messy
    -0.49
     yours
    -0.49
    POSITIVE LOGITS
    [
    3.75
    ,[
    2.42
    )[
    2.24
    [[
    2.14
    ["
    2.10
    [/
    2.07
    "[
    2.04
    ".[
    2.03
    ."[
    2.03
    .[
    2.02
    Activations Density 0.014%

    No Known Activations