© 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. 10-RES-JB
    11. 13991
    Prev
    Next
    INDEX
    Explanations

    mentions of activities related to American football, particularly focusing on the position of pass rusher

    oai_token-act-pair · gpt-3.5-turbo

    terms related to passing in football

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plur
    -0.85
    orporated
    -0.76
    henko
    -0.69
     Rohing
    -0.64
     Ples
    -0.64
     Milk
    -0.64
    CTV
    -0.62
     Males
    -0.62
    aiman
    -0.61
    opsis
    -0.61
    POSITIVE LOGITS
     rusher
    1.07
     rush
    0.92
    ivity
    0.89
     interference
    0.88
     catcher
    0.88
     muster
    0.86
     rushing
    0.86
     Passing
    0.82
     blocker
    0.78
     receptions
    0.77
    Activations Density 0.023%

    No Known Activations