© 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. 20349
    Prev
    Next
    INDEX
    Explanations

    information about different ethnic origins or descents

    oai_token-act-pair · gpt-3.5-turbo

    ethnic and national identities

    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
    odder
    -0.74
    uably
    -0.72
    ãĥ´ãĤ¡
    -0.71
    ause
    -0.69
    tracking
    -0.68
    forcement
    -0.68
    olicy
    -0.68
    perty
    -0.66
    olving
    -0.64
    hibit
    -0.63
    POSITIVE LOGITS
     immigrants
    1.47
     immigrant
    1.45
     descent
    1.36
     nationals
    1.33
     ancestry
    1.33
     nationality
    1.20
     ethnicity
    1.14
     heritage
    1.13
    istani
    1.13
     migrant
    1.12
    Activations Density 0.126%

    No Known Activations