© 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. 7-RES-JB
    11. 3191
    Prev
    Next
    INDEX
    Explanations

    keywords related to geopolitical events and countries

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical entities and their involvement in conflicts or agreements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stub
    -0.71
    rake
    -0.68
     glim
    -0.67
    arers
    -0.66
     Crow
    -0.65
     Rivers
    -0.65
     Finch
    -0.64
     seniors
    -0.64
     trim
    -0.63
     "$:/
    -0.63
    POSITIVE LOGITS
    Äĩ
    0.98
     Belarus
    0.97
    Ukraine
    0.96
    Äį
    0.96
     Ukraine
    0.95
     Monteneg
    0.92
     Ukrain
    0.91
    kaya
    0.90
     Lavrov
    0.89
     Putin
    0.89
    Activations Density 0.263%

    No Known Activations