© 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 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. 8-RES-JB
    11. 10773
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events and time periods, specifically focusing on World War II

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "World War" followed by ordinal numbers or related periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ibilities
    -0.85
    »Ĵ
    -0.79
    ibly
    -0.78
    IBLE
    -0.76
    ibility
    -0.75
    dq
    -0.75
    ible
    -0.67
    ippi
    -0.66
     pedals
    -0.66
    MENTS
    -0.64
    POSITIVE LOGITS
     Wide
    1.07
     Trade
    1.00
     Championships
    0.96
     Cup
    0.95
     Order
    0.91
    Tour
    0.90
     War
    0.89
    Wide
    0.89
     Airways
    0.89
     Bank
    0.88
    Activations Density 0.038%

    No Known Activations