© 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. 8-RES-JB
    11. 6944
    Prev
    Next
    INDEX
    Explanations

    characteristics related to social identity such as race, ethnicity, nationality, and religion

    oai_token-act-pair · gpt-3.5-turbo

    terms and references related to identity categories such as race, ethnicity, and nationality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sers
    -0.80
    ruck
    -0.78
    eus
    -0.75
     Canaver
    -0.72
    hiba
    -0.71
    ositories
    -0.71
     wat
    -0.71
    put
    -0.70
    nyder
    -0.68
    ocket
    -0.67
    POSITIVE LOGITS
     ethnicity
    1.61
     nationality
    1.48
     gender
    1.42
     ethnic
    1.37
     Gender
    1.18
     genders
    1.17
     Ethnic
    1.16
     socioeconomic
    1.14
    Gender
    1.13
    ethnic
    1.13
    Activations Density 0.131%

    No Known Activations