Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16177
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming, coding, specifically related to symbols and data types in programming languages, such as @, {, nil, and CSS

    oai_token-act-pair · gpt-3.5-turbo

    references to elements and attributes typically associated with programming or markup languages, particularly focusing on syntax elements

    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
     Tud
    -0.86
     Gillespie
    -0.84
     Ukrain
    -0.81
     Cassidy
    -0.76
     �
    -0.76
     Berman
    -0.76
     Driving
    -0.75
     revolving
    -0.74
     Marian
    -0.74
     Ven
    -0.73
    POSITIVE LOGITS
    foo
    1.51
    ignore
    1.44
    example
    1.41
    include
    1.40
    output
    1.40
    apply
    1.40
    message
    1.38
    input
    1.35
    callback
    1.35
    skip
    1.34
    Activations Density 0.091%

    No Known Activations