© 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. 11410
    Prev
    Next
    INDEX
    Explanations

    keywords and syntax related to programming languages, specifically class definitions and function declarations

    oai_token-act-pair · gpt-3.5-turbo

    programming constructs related to classes and variables

    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
    advertising
    -1.02
    agall
    -0.99
    conservancy
    -0.85
    leans
    -0.82
    fect
    -0.79
    ë
    -0.78
    Ãĥ
    -0.77
    ê
    -0.77
    IQ
    -0.77
    soDeliveryDate
    -0.77
    POSITIVE LOGITS
     Foo
    1.02
     Main
    0.97
     foo
    0.97
     Example
    0.95
     My
    0.93
     Default
    0.89
     _
    0.87
     User
    0.87
     Hello
    0.86
     main
    0.84
    Activations Density 0.046%

    No Known Activations