© 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. 231
    Prev
    Next
    INDEX
    Explanations

    mentions of countries, organizations, and events related to political news

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the end-of-text token and references to the United States

    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
    omever
    -0.54
    ilan
    -0.51
    alone
    -0.50
     respons
    -0.50
    actively
    -0.50
    posts
    -0.50
     alike
    -0.50
    enegger
    -0.49
     elsewhere
    -0.49
    cially
    -0.48
    POSITIVE LOGITS
     Encyclopedia
    0.82
     Library
    0.76
     Dictionary
    0.75
     Museum
    0.74
     Bulletin
    0.72
     Nebula
    0.71
     Gazette
    0.69
     Association
    0.69
     Securities
    0.68
     Catalog
    0.68
    Activations Density 0.343%

    No Known Activations