© 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 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. 0-RES-JB
    11. 10005
    Prev
    Next
    INDEX
    Explanations

    keywords related to the sport of golf

    oai_token-act-pair · gpt-3.5-turbo

    terms related to golf and sporting events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     angel
    -0.87
     garg
    -0.86
     scal
    -0.77
     electroly
    -0.76
     emoji
    -0.76
     chains
    -0.74
     cruc
    -0.74
     demon
    -0.74
     blockers
    -0.74
     mac
    -0.73
    POSITIVE LOGITS
     Golf
    2.93
     Sporting
    2.28
     Tennis
    1.86
     Athletic
    1.62
     Polo
    1.62
     Sports
    1.50
     Boxing
    1.50
     Recreation
    1.50
     Racing
    1.50
     Ski
    1.46
    Activations Density 0.034%

    No Known Activations