© 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. 7776
    Prev
    Next
    INDEX
    Explanations

    countries and regions in Eastern Europe

    oai_token-act-pair · gpt-3.5-turbo

    mentions of European countries and related geographical references

    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
     WATCHED
    -0.76
    artisan
    -0.76
    hari
    -0.73
    DragonMagazine
    -0.69
    ript
    -0.68
    inventoryQuantity
    -0.68
    ertodd
    -0.67
     Mahjong
    -0.66
     ballpark
    -0.66
    RAFT
    -0.66
    POSITIVE LOGITS
     Lithuania
    1.81
     Latvia
    1.80
     Slovakia
    1.77
     Hungary
    1.71
     Slovenia
    1.66
     Bulgaria
    1.65
     Estonia
    1.64
     Denmark
    1.59
     Portugal
    1.58
     Romania
    1.58
    Activations Density 0.141%

    No Known Activations