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. 3632
    Prev
    Next
    INDEX
    Explanations

    phrases related to laughter or humor

    oai_token-act-pair · gpt-3.5-turbo

    references to laughter and its contextual relationships with children and families

    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
     Comet
    -0.68
    ̶
    -0.66
    claimer
    -0.65
    acea
    -0.63
     Dive
    -0.62
    stro
    -0.62
    ron
    -0.62
     Tropical
    -0.62
     Airlines
    -0.59
     Phant
    -0.59
    POSITIVE LOGITS
    aughter
    3.20
    aughters
    1.89
     authority
    1.59
    laughter
    0.87
    children
    0.77
    aughtered
    0.76
    externalActionCode
    0.75
     responsibility
    0.75
    uary
    0.74
    enary
    0.73
    Activations Density 0.004%

    No Known Activations