© 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. 14162
    Prev
    Next
    INDEX
    Explanations

    actions or strategies related to sports, especially football

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to sports strategy and player positioning

    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
     Adventures
    -0.69
     Straw
    -0.64
     Annual
    -0.63
     Lumin
    -0.62
     Rowling
    -0.62
     Generations
    -0.62
     Woo
    -0.61
     Epic
    -0.61
     slogans
    -0.61
     Patreon
    -0.59
    POSITIVE LOGITS
     underneath
    1.02
     backfield
    1.00
     drib
    0.97
     blocker
    0.94
     defensively
    0.94
     defenders
    0.94
     defender
    0.93
     stride
    0.93
     vertically
    0.92
     guarding
    0.92
    Activations Density 0.178%

    No Known Activations