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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 15276
    Prev
    Next
    INDEX
    Explanations

    phrases and names related to North Korean leader Kim Jong Un

    oai_token-act-pair · gpt-3.5-turbo

    references to Kim Jong-un and leadership in North Korea

    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
    Recommend
    -0.86
     lineback
    -0.82
    nesota
    -0.80
    Wisconsin
    -0.79
    Scot
    -0.78
     Leigh
    -0.77
    Lex
    -0.76
     Dunn
    -0.76
     Uncharted
    -0.75
     Wilmington
    -0.73
    POSITIVE LOGITS
     Jinping
    1.28
     assassinated
    1.17
     dictator
    1.17
     dictatorship
    1.09
     regime
    1.07
     authoritarian
    1.07
     himself
    1.04
     tyrant
    0.97
     Gaddafi
    0.97
    addafi
    0.97
    Activations Density 0.412%

    No Known Activations