© 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. 1881
    Prev
    Next
    INDEX
    Explanations

    terms related to sports, particularly football (soccer) where players interact with the ball

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "ball" in various contexts

    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
    SPONSORED
    -0.82
     Micha
    -0.78
    erenn
    -0.77
     Sina
    -0.73
    iots
    -0.72
     Siber
    -0.72
     Emin
    -0.71
     Tayyip
    -0.71
     HTC
    -0.70
     Synd
    -0.69
    POSITIVE LOGITS
     ball
    3.69
     balls
    2.53
     Ball
    2.32
    Ball
    2.29
    ball
    2.28
     BALL
    1.97
     puck
    1.92
    BALL
    1.74
    balls
    1.72
     Balls
    1.62
    Activations Density 0.008%

    No Known Activations