© 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. 11-RES-JB
    11. 22523
    Prev
    Next
    INDEX
    Explanations

    significant events or trends in various historical contexts, such as political elections, economic recessions, legislative changes, and social crises

    oai_token-act-pair · gpt-3.5-turbo

    references to significant political events or crises in history

    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
    ById
    -0.76
    ãĤ³
    -0.68
    tie
    -0.65
     everywhere
    -0.64
    gravity
    -0.64
    odder
    -0.63
    çķ
    -0.63
    aida
    -0.63
    idity
    -0.62
    lux
    -0.62
    POSITIVE LOGITS
     history
    1.37
    history
    1.19
     decades
    1.07
     History
    1.06
     recorded
    1.02
     memory
    0.99
     modern
    0.98
     recent
    0.98
     postwar
    0.96
     generations
    0.89
    Activations Density 0.059%

    No Known Activations