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. 10-RES-JB
    6. 8950
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, particularly related to code execution and configuration

    oai_token-act-pair · gpt-3.5-turbo
    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
    AIDS
    -0.82
     Oprah
    -0.73
    assault
    -0.71
    Alabama
    -0.70
    America
    -0.69
    ampunk
    -0.69
    Americ
    -0.67
    African
    -0.66
     America
    -0.66
    arians
    -0.66
    POSITIVE LOGITS
     bunch
    1.06
     static
    1.02
     subset
    1.01
     comma
    1.00
     separate
    0.99
     single
    0.98
     few
    0.98
     recursive
    0.97
     dummy
    0.97
     simple
    0.96
    Activations Density 0.190%

    No Known Activations