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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4-RES-JB
    11. 14938
    Prev
    Next
    INDEX
    Explanations

    phrases related to geographic locations, specifically focusing on the Czech Republic

    oai_token-act-pair · gpt-3.5-turbo

    references to the Czech Republic and its capital, Prague

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

    No Comments

    Negative Logits
    ciating
    -0.90
    LEASE
    -0.87
    natureconservancy
    -0.83
    utherford
    -0.82
    nels
    -0.80
    wered
    -0.77
    WARD
    -0.74
    inventoryQuantity
    -0.74
    phasis
    -0.73
    Oracle
    -0.73
    POSITIVE LOGITS
    oslov
    2.08
     Republic
    1.12
    oslav
    1.09
    istani
    1.00
    ski
    0.89
     Czech
    0.85
     Slov
    0.78
    Republic
    0.77
     Boh
    0.77
     nationals
    0.76
    Activations Density 0.011%

    No Known Activations