© 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. 8-RES-JB
    11. 2584
    Prev
    Next
    INDEX
    Explanations

    organizations or entities related to regulations and governance, specifically focusing on the Food and Drug Administration in the United States

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the conjunction "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hower
    -0.79
    chev
    -0.79
    helps
    -0.73
    bos
    -0.72
    sole
    -0.69
    wolf
    -0.68
    igmatic
    -0.67
    ses
    -0.67
    ixel
    -0.65
    figure
    -0.63
    POSITIVE LOGITS
     Fitness
    0.92
     Services
    0.90
     Markets
    0.88
     Environmental
    0.88
     Entertainment
    0.85
     Transportation
    0.85
     Drug
    0.85
     Development
    0.82
     Electronics
    0.82
     Aging
    0.81
    Activations Density 0.085%

    No Known Activations