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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 431
    Prev
    Next
    INDEX
    Explanations

    mentions related to historical events involving the Ottoman Empire

    oai_token-act-pair · gpt-3.5-turbo

    references to the Ottoman Empire and related historical figures

    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
    ritch
    -0.78
    llo
    -0.78
    lla
    -0.76
    leading
    -0.72
    rigan
    -0.69
    etimes
    -0.68
    ecycle
    -0.67
    verage
    -0.65
    cheon
    -0.64
    leton
    -0.64
    POSITIVE LOGITS
     Seym
    0.89
     Jordanian
    0.84
    oola
    0.82
     Sultan
    0.79
     Maya
    0.78
     "$:/
    0.74
     Ottoman
    0.72
    ¢
    0.72
    conservancy
    0.71
     Sheikh
    0.69
    Activations Density 0.032%

    No Known Activations