© 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. 13518
    Prev
    Next
    INDEX
    Explanations

    terms related to sports leagues, teams, and players

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports leagues and associations

    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
    luaj
    -0.68
    nih
    -0.67
    emonic
    -0.66
     Kurd
    -0.64
    otte
    -0.64
    OHN
    -0.61
    ICE
    -0.60
     MacArthur
    -0.59
    agraph
    -0.59
     Rockefeller
    -0.59
    POSITIVE LOGITS
    interstitial
    0.75
    ateurs
    0.73
     Franch
    0.72
    athlon
    0.70
    riors
    0.65
     Gleaming
    0.65
     Recre
    0.65
     trout
    0.65
     hoop
    0.64
    enegger
    0.64
    Activations Density 0.356%

    No Known Activations