Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20893
    Prev
    Next
    INDEX
    Explanations

    mentions of political leaders, specifically focusing on the name "Kim Jong Un" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to North Korean leaders, particularly Kim Jong-un and related lineage

    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
    iott
    -0.73
    uary
    -0.71
     Phillies
    -0.67
    mble
    -0.67
     Arkham
    -0.66
    ource
    -0.66
    aukee
    -0.65
     Delaware
    -0.65
    Irish
    -0.64
    Ireland
    -0.64
    POSITIVE LOGITS
     Jong
    1.40
     Jinping
    1.38
     Yong
    1.18
    ongyang
    1.16
     Xi
    1.10
     Ji
    1.08
     Chong
    1.07
     Xia
    1.07
     Il
    1.04
     Qian
    1.03
    Activations Density 0.050%

    No Known Activations