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. 0-RES-JB
    6. 17058
    Prev
    Next
    INDEX
    Explanations

    references to territorial disputes or territorial integrity in geopolitical contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to territorial and maritime issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esson
    -0.72
     Reviews
    -0.71
    wra
    -0.68
    watch
    -0.68
     Huma
    -0.64
     Side
    -0.64
    Edit
    -0.63
    osen
    -0.62
    Tw
    -0.62
    Tools
    -0.61
    POSITIVE LOGITS
     territorial
    3.90
     Territ
    1.79
     territ
    1.63
     territory
    1.49
     jurisd
    1.45
     Territory
    1.36
     maritime
    1.31
     sovereignty
    1.29
     territories
    1.17
     geographical
    1.14
    Activations Density 0.014%

    No Known Activations