© 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. 1-RES-JB
    11. 11370
    Prev
    Next
    INDEX
    Explanations

    mentions of names related to Asian origin

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to individuals, particularly those with the name "Kang" or "Jung"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vation
    -0.87
    Course
    -0.87
    20439
    -0.85
    prises
    -0.84
    ãĥīãĥ©
    -0.80
    ×ķ
    -0.75
    alysis
    -0.73
    prise
    -0.72
     CODE
    -0.70
    clair
    -0.70
    POSITIVE LOGITS
     Kang
    1.06
    aroo
    0.95
     Jung
    0.95
    yrinth
    0.94
    aign
    0.80
     Hamm
    0.79
    arding
    0.78
    inal
    0.76
    iov
    0.76
    ulative
    0.74
    Activations Density 0.021%

    No Known Activations