© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5115
    Prev
    Next
    INDEX
    Explanations

    terms related to software programming and development methodologies, specifically focusing on differences between programming languages and concepts such as dynamic and lexical scoping

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms related to dynamic and static programming concepts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    mare
    -0.84
    mares
    -0.78
    ĨĴ
    -0.75
    bring
    -0.71
     Meredith
    -0.69
    umi
    -0.67
    warts
    -0.67
    acular
    -0.67
    chen
    -0.67
    apolis
    -0.66
    POSITIVE LOGITS
     analy
    0.88
     Duo
    0.87
     typing
    0.79
     electricity
    0.76
     linking
    0.75
     analys
    0.73
    hess
    0.72
     analysis
    0.72
     pricing
    0.71
    ity
    0.71
    Activations Density 0.077%

    No Known Activations