© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 6272
    Prev
    Next
    INDEX
    Explanations

    references to Indigenous communities or peoples

    oai_token-act-pair · gpt-3.5-turbo

    references to Indigenous and Native American groups and issues

    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
    ueller
    -0.82
    ãĥ´ãĤ¡
    -0.76
    abl
    -0.75
    oldemort
    -0.74
    ilion
    -0.73
    ector
    -0.72
    inventoryQuantity
    -0.70
    âĸł
    -0.70
    ysis
    -0.69
    =-=-=-=-=-=-=-=-
    -0.69
    POSITIVE LOGITS
     peoples
    1.12
     Peoples
    1.10
     tribes
    1.09
     tribe
    1.01
     Tribal
    0.98
     Sioux
    0.96
     communities
    0.93
     Nations
    0.92
     Navajo
    0.91
     tribal
    0.89
    Activations Density 0.071%

    No Known Activations