© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 20648
    Prev
    Next
    INDEX
    Explanations

    mentions of the country "North Korea"

    oai_token-act-pair · gpt-3.5-turbo

    references to North Korea and related geopolitical topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "$:/
    -0.87
    TABLE
    -0.83
    TED
    -0.73
    series
    -0.73
    dx
    -0.72
    TIME
    -0.70
    0200
    -0.70
    CLUS
    -0.70
    natureconservancy
    -0.70
    reviewed
    -0.69
    POSITIVE LOGITS
     Korea
    1.25
     Koreans
    1.23
     Korean
    1.06
    ongyang
    1.02
    uclear
    0.89
     Jong
    0.86
     Pyongyang
    0.83
     missile
    0.83
     Kurdistan
    0.77
    ijing
    0.73
    Activations Density 0.033%

    No Known Activations