© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4987
    Prev
    Next
    INDEX
    Explanations

    details related to international relations and disputes, particularly involving China, the United States, and neighboring countries like Taiwan

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases related to military presence and territorial disputes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Sabb
    -0.83
     MPG
    -0.82
    ÃŃ
    -0.79
     Croatian
    -0.78
    ÙĪ
    -0.75
     Javascript
    -0.74
     Comet
    -0.74
     Frankenstein
    -0.73
    ÙĬ
    -0.73
    ̶
    -0.73
    POSITIVE LOGITS
     Beijing
    1.47
     PLA
    1.47
     Seoul
    1.41
     Taiwan
    1.34
    China
    1.23
     China
    1.23
     Taiwanese
    1.17
     Tokyo
    1.16
     Guam
    1.14
    Tai
    1.13
    Activations Density 0.322%

    No Known Activations