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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13514
    Prev
    Next
    INDEX
    Explanations

    terms related to physical exercise, specifically focusing on weightlifting and strength training

    oai_token-act-pair · gpt-3.5-turbo

    mentions of benches

    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
    alez
    -0.74
    lia
    -0.73
    yles
    -0.69
    actionDate
    -0.69
    pires
    -0.68
    lers
    -0.66
    mber
    -0.66
    ually
    -0.66
    odi
    -0.66
     Rings
    -0.65
    POSITIVE LOGITS
    warm
    1.15
    tops
    0.86
    mark
    0.86
    lain
    0.85
    marked
    0.84
     benches
    0.82
    top
    0.79
    iron
    0.79
    ing
    0.78
     warrants
    0.77
    Activations Density 0.037%

    No Known Activations