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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 21053
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical regions or countries, specifically focusing on the Middle Eastern region

    oai_token-act-pair · gpt-3.5-turbo

    references to the Eastern region, specifically in geographical or cultural contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    papers
    -0.75
    ppo
    -0.70
    arium
    -0.69
    netflix
    -0.68
     profiling
    -0.65
    QUI
    -0.64
     spills
    -0.64
    wagen
    -0.63
    isable
    -0.63
     Goo
    -0.62
    POSITIVE LOGITS
     Eastern
    3.68
    Eastern
    3.13
     eastern
    2.43
     Western
    2.03
     East
    1.95
    Western
    1.78
    East
    1.63
     western
    1.59
     Northern
    1.57
    astern
    1.55
    Activations Density 0.016%

    No Known Activations