Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2152
    Prev
    Next
    INDEX
    Explanations

    terms related to scoring goals in sports, specifically ice hockey

    oai_token-act-pair · gpt-3.5-turbo

    references to scoring goals in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.82
     Rollins
    -0.68
    abus
    -0.66
    iannopoulos
    -0.64
    Operation
    -0.64
     Solitaire
    -0.63
     sclerosis
    -0.62
    orld
    -0.61
     discounts
    -0.60
    FY
    -0.60
    POSITIVE LOGITS
    keepers
    1.15
    keeping
    1.12
     scorer
    1.07
    stre
    1.04
    keeper
    1.03
     scored
    1.02
    core
    1.01
    scoring
    0.93
    mouth
    0.93
     conceded
    0.90
    Activations Density 0.037%

    No Known Activations