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. 0-RES-JB
    6. 21338
    Prev
    Next
    INDEX
    Explanations

    phrases related to audience reactions like clapping and cheering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to audience reactions, specifically applause and cheers

    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
    wi
    -0.71
     located
    -0.66
     locating
    -0.63
    neys
    -0.62
     mapped
    -0.62
    letal
    -0.61
    dependent
    -0.61
     operated
    -0.59
    shop
    -0.59
    controlled
    -0.59
    POSITIVE LOGITS
     applause
    4.07
     cheers
    2.84
     cheering
    1.47
     laughter
    1.46
     congratulations
    1.43
     laughs
    1.37
     applaud
    1.35
     praise
    1.32
     acclaim
    1.32
    laughter
    1.27
    Activations Density 0.021%

    No Known Activations