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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23880
    Prev
    Next
    INDEX
    Explanations

    actions related to physical sports activities, especially those involving fast movements and making quick decisions

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of athletic performance and skills

    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
    yll
    -0.81
    onym
    -0.79
    DragonMagazine
    -0.74
     Adult
    -0.74
    odiac
    -0.73
    ophon
    -0.72
    Adult
    -0.71
    ederal
    -0.71
    wives
    -0.70
    reviewed
    -0.69
    POSITIVE LOGITS
     drib
    1.17
     defensively
    1.16
     turnovers
    1.08
     deflect
    1.06
     pressuring
    1.05
     offensively
    1.04
     rebound
    1.03
     rebounds
    1.03
     blitz
    1.02
     whiff
    1.01
    Activations Density 0.197%

    No Known Activations