© 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. 1154
    Prev
    Next
    INDEX
    Explanations

    dates and historical events in the 1980s, specifically mentioning various places and universities

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and time periods

    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
     Crimean
    -0.82
    cius
    -0.73
     Baghd
    -0.73
    eenth
    -0.69
    phabet
    -0.68
     Jenkins
    -0.67
    usc
    -0.67
    hole
    -0.65
    riet
    -0.65
    ailable
    -0.64
    POSITIVE LOGITS
     1981
    1.92
     1983
    1.90
     1985
    1.90
     1982
    1.88
     1987
    1.87
     1986
    1.87
     1988
    1.85
     1984
    1.83
     1989
    1.79
    1982
    1.75
    Activations Density 0.169%

    No Known Activations