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

    Neuronpedia

    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. 11-RES-JB
    11. 7737
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, specifically those related to World War I and World War II

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "World War."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pled
    -0.81
    */(
    -0.78
    aryn
    -0.72
    IBLE
    -0.72
     porous
    -0.69
     nod
    -0.69
    dq
    -0.69
     plea
    -0.66
     plank
    -0.65
     nails
    -0.65
    POSITIVE LOGITS
     War
    1.46
     Wars
    1.16
     Trade
    1.09
    war
    1.07
    War
    1.06
     war
    0.91
     Crusade
    0.88
     Communism
    0.88
     Warcraft
    0.88
     Peace
    0.87
    Activations Density 0.021%

    No Known Activations