© 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. 0-RES-JB
    11. 1995
    Prev
    Next
    INDEX
    Explanations

    Native Hawaiian, Cherokee, and Navajo related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to specific ethnic groups, particularly Hawaiian, Cherokee, and Navajo identities

    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
     Cry
    -0.76
    uthor
    -0.75
     Vlad
    -0.73
    orthy
    -0.73
    beit
    -0.69
    iment
    -0.68
    ============
    -0.68
    lvl
    -0.67
     defect
    -0.67
    GD
    -0.66
    POSITIVE LOGITS
     Hawaiian
    3.32
     Hawai
    2.61
     Navajo
    2.22
     Cherokee
    1.80
    Haw
    1.55
     Chero
    1.33
     Honolulu
    1.27
     Appalachian
    1.07
     Klingon
    1.05
     Iro
    1.00
    Activations Density 0.053%

    No Known Activations