© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 21068
    Prev
    Next
    INDEX
    Explanations

    phrases related to cricket bowling performance

    oai_token-act-pair · gpt-3.5-turbo

    references to sports statistics and player performance

    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
     Lyft
    -0.97
     Ukrain
    -0.83
    oros
    -0.83
    ominium
    -0.82
    Moscow
    -0.81
     Byzantine
    -0.80
     Downtown
    -0.80
     Orthodox
    -0.79
    ÅŁ
    -0.78
    Syrian
    -0.77
    POSITIVE LOGITS
     cricket
    1.83
     Cricket
    1.69
     batting
    1.62
     bowling
    1.62
     Ashes
    1.57
     bats
    1.57
     Tests
    1.54
     innings
    1.50
     Sri
    1.35
     Test
    1.34
    Activations Density 0.264%

    No Known Activations