© 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. 4-RES-JB
    11. 10672
    Prev
    Next
    INDEX
    Explanations

    references to the word "Sport"

    oai_token-act-pair · gpt-3.5-turbo

    frequent mentions of the term "Sport" in various contexts

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

    No Comments

    Negative Logits
    osures
    -0.72
    izons
    -0.72
     Kaplan
    -0.70
     externalToEVAOnly
    -0.69
     unborn
    -0.68
    anked
    -0.67
    maxwell
    -0.67
     convincing
    -0.66
    ennial
    -0.66
    utations
    -0.65
    POSITIVE LOGITS
    Sport
    1.18
     Sport
    1.06
    sw
    0.99
    scar
    0.93
    ster
    0.88
     Club
    0.87
     Wrestling
    0.87
    club
    0.86
    sports
    0.83
    wagen
    0.83
    Activations Density 0.012%

    No Known Activations