© 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. 7-RES-JB
    11. 20697
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions and movements, especially in sports contexts

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to physical actions or techniques in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Governments
    -0.87
    IENT
    -0.86
    actionDate
    -0.82
    Month
    -0.78
    Government
    -0.78
     Administ
    -0.77
    Monitor
    -0.76
    mbuds
    -0.76
    icter
    -0.75
    Fund
    -0.75
    POSITIVE LOGITS
     fastball
    1.06
     dunk
    1.02
     shots
    1.01
     takedown
    0.96
     punches
    0.96
     volley
    0.95
     knockout
    0.95
     punch
    0.95
     snatch
    0.94
     choke
    0.93
    Activations Density 0.342%

    No Known Activations