© 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. 11-RES-JB
    11. 7678
    Prev
    Next
    INDEX
    Explanations

    mentions of different countries and their relationships or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    geographical names and references to countries and regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     DeV
    -0.62
    asonable
    -0.61
    Ward
    -0.61
    plain
    -0.60
     Perkins
    -0.59
    uum
    -0.59
    ulty
    -0.58
    evin
    -0.57
    elle
    -0.57
    smith
    -0.54
    POSITIVE LOGITS
     Countries
    1.12
     Nato
    1.08
     countries
    1.06
     Balkans
    1.06
     geopolitical
    1.05
     NATO
    1.05
     Albania
    1.01
     bilateral
    1.01
     Asia
    1.01
    Asia
    1.00
    Activations Density 0.673%

    No Known Activations