© 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. 8-RES-JB
    11. 22371
    Prev
    Next
    INDEX
    Explanations

    instances where African-Americans are mentioned or referenced

    oai_token-act-pair · gpt-3.5-turbo

    references to the African American community and issues related to them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shutter
    -0.77
     Shutterstock
    -0.72
     Prol
    -0.68
     dossier
    -0.64
     ellipt
    -0.64
     Lovecraft
    -0.63
     physic
    -0.62
     HL
    -0.62
     pse
    -0.62
     disinfect
    -0.62
    POSITIVE LOGITS
    American
    1.26
    Americans
    1.13
    amer
    0.97
    America
    0.97
    origin
    0.95
    immigrant
    0.95
    themed
    0.93
    sounding
    0.92
    affiliated
    0.90
    Pacific
    0.90
    Activations Density 0.031%

    No Known Activations