Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3307
    Prev
    Next
    INDEX
    Explanations

    locations and countries, particularly focusing on the Czech Republic

    oai_token-act-pair · gpt-3.5-turbo

    references to the Czech Republic and its capital city, Prague

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.92
    ciating
    -0.88
    nels
    -0.78
    cule
    -0.78
    utherford
    -0.74
    aeda
    -0.74
    LEASE
    -0.71
    htar
    -0.70
    ufact
    -0.70
    inventoryQuantity
    -0.68
    POSITIVE LOGITS
    oslov
    2.05
    oslav
    1.17
     Republic
    1.13
    ski
    0.91
    istani
    0.86
    Republic
    0.83
    sky
    0.81
    s
    0.78
    sis
    0.77
    sylvania
    0.77
    Activations Density 0.018%

    No Known Activations