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

    Neuronpedia

    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. 9-RES-JB
    11. 15654
    Prev
    Next
    INDEX
    Explanations

    references to geopolitical relationships and international conflicts

    oai_token-act-pair · gpt-3.5-turbo

    geopolitical terms and historical events related to international relations

    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
    odder
    -0.73
     Architects
    -0.71
     Insp
    -0.70
     Manson
    -0.70
    ateurs
    -0.70
    ertation
    -0.70
    shown
    -0.70
    thouse
    -0.69
     Darrell
    -0.68
     Rudolph
    -0.67
    POSITIVE LOGITS
     bilateral
    1.39
     treaties
    1.39
     relations
    1.34
     treaty
    1.33
     negotiations
    1.33
     conflict
    1.31
     alliances
    1.30
     dispute
    1.25
     relationship
    1.24
     ceasefire
    1.23
    Activations Density 1.383%

    No Known Activations