© 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. 22230
    Prev
    Next
    INDEX
    Explanations

    words related to cricket

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to cricket, particularly the players and their roles

    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
    DragonMagazine
    -0.78
    owntown
    -0.70
    Crime
    -0.70
    onomous
    -0.69
    ãĥ´ãĤ¡
    -0.67
    hattan
    -0.66
     Scotia
    -0.64
    £ı
    -0.64
    issy
    -0.63
    utterstock
    -0.62
    POSITIVE LOGITS
     batting
    1.00
     cricket
    0.94
     batted
    0.92
    ickets
    0.90
     bowling
    0.87
     defences
    0.86
     Cricket
    0.82
     darts
    0.81
    glers
    0.78
     bats
    0.76
    Activations Density 0.023%

    No Known Activations