© 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. 0-RES-JB
    11. 8263
    Prev
    Next
    INDEX
    Explanations

    the word "Global"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Global" and organizations or concepts associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rats
    -0.76
    artifacts
    -0.73
     amuse
    -0.73
    umber
    -0.66
     pudding
    -0.66
    berries
    -0.65
     inval
    -0.65
    essa
    -0.65
     baths
    -0.65
     stout
    -0.65
    POSITIVE LOGITS
     Global
    3.57
    Global
    2.82
    global
    2.49
     global
    2.14
     Worldwide
    1.64
     globally
    1.58
     globalization
    1.51
     International
    1.48
     Glob
    1.45
    International
    1.28
    Activations Density 0.009%

    No Known Activations