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. 15809
    Prev
    Next
    INDEX
    Explanations

    details about different ethnic communities and their histories

    oai_token-act-pair · gpt-3.5-turbo

    references to ethnic and religious communities and their histories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    inventoryQuantity
    -1.00
    Zero
    -0.83
    quickShipAvailable
    -0.81
     PowerPoint
    -0.80
     Investigator
    -0.78
     VIDEOS
    -0.78
    launch
    -0.76
    RH
    -0.76
    ocket
    -0.75
    DCS
    -0.75
    POSITIVE LOGITS
     assimil
    1.52
     migrated
    1.47
     descendants
    1.36
     migrating
    1.34
     ethn
    1.34
     settlers
    1.32
     migrate
    1.30
     persecuted
    1.28
     ancestral
    1.28
     enslaved
    1.25
    Activations Density 0.585%

    No Known Activations