© 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. 15710
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical tensions and territorial disputes

    oai_token-act-pair · gpt-3.5-turbo

    references to disputed territories and geopolitical tensions

    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
     Dealer
    -0.78
    mith
    -0.72
     hairc
    -0.72
    Adult
    -0.72
    smith
    -0.72
     mold
    -0.71
    Avg
    -0.69
    Professional
    -0.68
    Engine
    -0.68
    wcsstore
    -0.67
    POSITIVE LOGITS
     disputed
    1.36
     islands
    1.31
     airspace
    1.21
     territories
    1.11
     annexed
    1.09
     territory
    1.08
     peninsula
    1.07
     border
    1.05
     Crimea
    1.04
     borders
    1.03
    Activations Density 0.329%

    No Known Activations