© 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. 7-RES-JB
    11. 17229
    Prev
    Next
    INDEX
    Explanations

    references to African Americans

    oai_token-act-pair · gpt-3.5-turbo

    mentions and references to African Americans

    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
    ertodd
    -0.80
    mble
    -0.77
    aminer
    -0.74
    alty
    -0.73
    igation
    -0.72
    DCS
    -0.72
    swer
    -0.69
    yip
    -0.69
    lag
    -0.69
    ysc
    -0.69
    POSITIVE LOGITS
     Methodist
    1.00
    American
    0.84
    Americans
    0.81
     Americans
    0.77
     American
    0.75
    ized
    0.71
     tribes
    0.70
    immigrant
    0.70
     Union
    0.70
    ishly
    0.69
    Activations Density 0.023%

    No Known Activations