© 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. 18653
    Prev
    Next
    INDEX
    Explanations

    code syntax and computer programming related keywords and symbols

    oai_token-act-pair · gpt-3.5-turbo

    structural elements and formatting in coding or programming-related content

    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
     metic
    -0.95
     Pigs
    -0.89
     Jericho
    -0.85
     Marketing
    -0.84
     Kits
    -0.80
     Derby
    -0.79
     BART
    -0.78
     Thrones
    -0.78
     Mayhem
    -0.77
     Restaur
    -0.77
    POSITIVE LOGITS
    lower
    1.52
    double
    1.51
    drop
    1.51
    null
    1.50
    another
    1.48
    new
    1.47
    window
    1.46
    div
    1.45
    distance
    1.44
    delete
    1.43
    Activations Density 0.206%

    No Known Activations