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. 8-RES-JB
    6. 19609
    Prev
    Next
    INDEX
    Explanations

    references to laughter or situations where laughter occurs

    oai_token-act-pair · gpt-3.5-turbo

    instances of laughter and references to laughing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tnc
    -0.73
     particulars
    -0.62
     Components
    -0.61
     mater
    -0.61
    esthetic
    -0.60
    forums
    -0.60
     cryst
    -0.59
    enture
    -0.58
    ctr
    -0.58
    change
    -0.57
    POSITIVE LOGITS
    ously
    0.99
     hyster
    0.98
     uproar
    0.95
    ably
    0.95
    ingly
    0.90
    sticks
    0.87
    lihood
    0.81
     maniac
    0.79
     nervously
    0.75
     Laugh
    0.75
    Activations Density 0.033%

    No Known Activations