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. 7-RES-JB
    6. 8294
    Prev
    Next
    INDEX
    Explanations

    references to different cultural groups and locations

    oai_token-act-pair · gpt-3.5-turbo

    specific ethnic or cultural identifiers and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.86
     srfAttach
    -0.78
    quickShipAvailable
    -0.74
    cially
    -0.73
     Turing
    -0.71
    theless
    -0.71
    )=(
    -0.70
    aminer
    -0.70
    shown
    -0.69
    ãĥ¼ãĥ³
    -0.65
    POSITIVE LOGITS
    nian
    1.00
     clans
    0.96
     tribes
    0.94
     nationalists
    0.91
    istani
    0.91
     tribal
    0.91
     settlers
    0.90
     villagers
    0.90
     villages
    0.88
     tribe
    0.86
    Activations Density 0.401%

    No Known Activations