© 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. 10-RES-JB
    11. 3346
    Prev
    Next
    INDEX
    Explanations

    mentions of different ethnic groups or conflicts related to ethnicity

    oai_token-act-pair · gpt-3.5-turbo

    references to ethnic groups and their characteristics or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uden
    -0.89
    soDeliveryDate
    -0.87
    ertodd
    -0.84
    tower
    -0.84
    agher
    -0.83
    awaru
    -0.80
    DERR
    -0.73
    inventoryQuantity
    -0.73
    OHN
    -0.73
    ilton
    -0.72
    POSITIVE LOGITS
     cleansing
    1.30
     minorities
    1.24
    ities
    1.22
     minority
    1.05
     groups
    0.97
     profiling
    0.89
     nationalists
    0.89
     slurs
    0.89
     nationalism
    0.88
     diversity
    0.87
    Activations Density 0.045%

    No Known Activations