© 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. 0-RES-JB
    11. 2394
    Prev
    Next
    INDEX
    Explanations

    references to African-related words or terms

    oai_token-act-pair · gpt-3.5-turbo

    references to African people or cultures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bots
    -0.80
    route
    -0.69
    bot
    -0.67
     destro
    -0.67
     Logged
    -0.65
     shutdown
    -0.65
     login
    -0.64
     recharge
    -0.63
     Weld
    -0.62
    ovsky
    -0.61
    POSITIVE LOGITS
     African
    3.64
    African
    3.22
     Africans
    2.72
     Africa
    2.28
     Afric
    2.16
     Ethiopian
    2.09
     Asian
    1.90
     Somali
    1.88
     Negro
    1.85
     Nigerian
    1.81
    Activations Density 0.011%

    No Known Activations