© 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. 11-RES-JB
    11. 22094
    Prev
    Next
    INDEX
    Explanations

    terms related to race and discrimination

    oai_token-act-pair · gpt-3.5-turbo

    topics related to systemic racism and racial inequality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Imaging
    -0.78
    ãĥŁ
    -0.76
    Offline
    -0.75
    arij
    -0.73
    */(
    -0.72
     Helic
    -0.71
     PET
    -0.71
    glers
    -0.70
     buds
    -0.69
    VPN
    -0.69
    POSITIVE LOGITS
     blacks
    2.25
     whites
    2.09
     Negro
    2.08
     racial
    2.02
     Blacks
    1.98
     racially
    1.93
     black
    1.92
     white
    1.90
    racial
    1.90
     African
    1.84
    Activations Density 0.859%

    No Known Activations