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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 14604
    Prev
    Next
    INDEX
    Explanations

    terms related to sports, specifically baseball

    oai_token-act-pair · gpt-3.5-turbo

    mentions of baseball

    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
    •Sports-related features

    No Comments

    Negative Logits
    mble
    -0.83
    ainer
    -0.78
     Ples
    -0.76
    ablishment
    -0.73
     Lauder
    -0.71
    omething
    -0.70
    wered
    -0.68
    chev
    -0.68
    ylum
    -0.67
    imen
    -0.66
    POSITIVE LOGITS
     stadiums
    0.85
     pitchers
    0.77
    Players
    0.76
     stadium
    0.75
     bats
    0.74
     players
    0.73
     scholarships
    0.73
     pitcher
    0.73
     attire
    0.72
     tournaments
    0.71
    Activations Density 0.035%

    No Known Activations