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. 10-RES-JB
    6. 1641
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical disputes and territories

    oai_token-act-pair · gpt-3.5-turbo

    terms related to territorial disputes in the East and South China Seas

    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
     Sabb
    -0.90
    ̶
    -0.78
     Elijah
    -0.77
    ombies
    -0.76
    issance
    -0.76
    hall
    -0.74
    HC
    -0.73
    á½
    -0.72
    mith
    -0.72
    oyer
    -0.71
    POSITIVE LOGITS
     islands
    1.52
     reefs
    1.37
     disputed
    1.34
     maritime
    1.33
     territorial
    1.31
     Taiwan
    1.30
     airspace
    1.30
     sovereignty
    1.29
     Islands
    1.25
     Okinawa
    1.24
    Activations Density 0.271%

    No Known Activations