© 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. 9-RES-JB
    11. 18353
    Prev
    Next
    INDEX
    Explanations

    references to golf-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to golf courses and related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sof
    -0.69
     Reign
    -0.67
    nces
    -0.66
    FY
    -0.65
    illin
    -0.64
     ACS
    -0.64
    mone
    -0.63
     Debor
    -0.62
    ENCY
    -0.62
     Flavoring
    -0.60
    POSITIVE LOGITS
     golf
    1.09
     balls
    0.99
     Golf
    0.94
    ball
    0.93
     Clubs
    0.93
    club
    0.92
     clubhouse
    0.91
    iste
    0.87
    balls
    0.87
     carts
    0.86
    Activations Density 0.057%

    No Known Activations