© 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. 10-RES-JB
    11. 7049
    Prev
    Next
    INDEX
    Explanations

    references to the country of Korea or events/people related to Korea

    oai_token-act-pair · gpt-3.5-turbo

    references to Korea and related terms

    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
    ashtra
    -0.81
    llo
    -0.78
    clair
    -0.75
    eus
    -0.73
    ttes
    -0.71
    ault
    -0.71
    igue
    -0.71
    yard
    -0.71
     Mayweather
    -0.69
    hetically
    -0.69
    POSITIVE LOGITS
    orea
    1.22
     ì
    1.14
     peninsula
    1.12
     ë
    1.08
     Korea
    1.05
     Peninsula
    1.03
    ë
    1.00
     Sung
    0.96
     Jong
    0.94
     Korean
    0.94
    Activations Density 0.024%

    No Known Activations