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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 763
    Prev
    Next
    INDEX
    Explanations

    names related to a specific political figure "Kim Jong Un"

    oai_token-act-pair · gpt-3.5-turbo

    references to North Korean leaders, specifically those with the name "Kim Jong."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arians
    -0.76
    aneous
    -0.69
    Results
    -0.67
    ICAN
    -0.67
    ATTLE
    -0.67
    rawdownloadcloneembedreportprint
    -0.65
    BACK
    -0.65
     Leilan
    -0.63
    RGB
    -0.62
    advertisement
    -0.62
    POSITIVE LOGITS
     Jong
    0.93
    sung
    0.93
    ongyang
    0.88
    enei
    0.87
     Il
    0.86
     Suk
    0.82
     Nam
    0.81
    jri
    0.79
    zeb
    0.79
    lasses
    0.77
    Activations Density 0.035%

    No Known Activations