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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    11. 9898
    Prev
    Next
    INDEX
    Explanations

    mentions of race or ethnicity, specifically focusing on African-Americans

    oai_token-act-pair · gpt-3.5-turbo

    references to the African American community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Another quick list

    No Comments

    Negative Logits
    pload
    -0.80
     Shutterstock
    -0.77
     Dickinson
    -0.75
     Pastebin
    -0.72
     constitu
    -0.71
    orious
    -0.69
     shutter
    -0.68
     Scrib
    -0.66
     Prol
    -0.66
     Gutenberg
    -0.65
    POSITIVE LOGITS
    American
    1.17
    Americans
    1.11
    themed
    1.04
    inspired
    1.04
    based
    1.03
    related
    1.01
    origin
    1.01
    induced
    0.99
    sounding
    0.98
    derived
    0.97
    Activations Density 0.065%

    No Known Activations