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

    Neuronpedia

    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. 2-RES-JB
    11. 17083
    Prev
    Next
    INDEX
    Explanations

    terms related to scoring goals in sports

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "goal" in various contexts related to sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.76
    VAL
    -0.71
    DragonMagazine
    -0.68
    odes
    -0.67
    Versions
    -0.67
    --------------------------------------------------------
    -0.63
    jen
    -0.62
    cale
    -0.61
    Norm
    -0.60
    greg
    -0.60
    POSITIVE LOGITS
     kicker
    1.00
     scorer
    0.91
    goal
    0.85
    iste
    0.78
    keepers
    0.78
     striker
    0.77
    boards
    0.76
     touchdown
    0.73
    iola
    0.73
     scored
    0.72
    Activations Density 0.021%

    No Known Activations