© 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. 10845
    Prev
    Next
    INDEX
    Explanations

    references to World War II

    oai_token-act-pair · gpt-3.5-turbo

    references to historical events associated with World War

    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
    ibilities
    -0.92
    EStream
    -0.90
    veyard
    -0.85
    ibility
    -0.83
    ibly
    -0.80
    »Ĵ
    -0.79
    merce
    -0.78
    Downloadha
    -0.76
    WARE
    -0.73
     actionGroup
    -0.73
    POSITIVE LOGITS
     Wide
    0.88
     Championships
    0.88
     Trade
    0.87
     Order
    0.86
     Federation
    0.85
     Cup
    0.84
     Bank
    0.83
     Series
    0.83
     Heritage
    0.82
     Reincarn
    0.81
    Activations Density 0.028%

    No Known Activations