© 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. 11-RES-JB
    11. 18581
    Prev
    Next
    INDEX
    Explanations

    names of people, focusing specifically on names such as Murphy and Walsh

    oai_token-act-pair · gpt-3.5-turbo

    names that repeat frequently, specifically "Murphy" and "Walsh."

    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
    omaly
    -0.85
    ician
    -0.82
    wikipedia
    -0.73
    eka
    -0.72
    ciating
    -0.71
    gypt
    -0.71
    etsk
    -0.70
    change
    -0.69
    ĪĴ
    -0.69
    ologies
    -0.66
    POSITIVE LOGITS
    quist
    0.73
    ufact
    0.72
     QC
    0.70
     MLA
    0.69
    enegger
    0.68
     LLP
    0.67
    intosh
    0.66
    ming
    0.65
    town
    0.64
     Osw
    0.63
    Activations Density 0.124%

    No Known Activations