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. 7-RES-JB
    6. 18295
    Prev
    Next
    INDEX
    Explanations

    texts related to humor and jokes

    oai_token-act-pair · gpt-3.5-turbo

    different forms and expressions of humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holder
    -0.73
    ports
    -0.72
    ignty
    -0.70
     opio
    -0.70
     cryst
    -0.64
     consolid
    -0.62
    eus
    -0.62
    minster
    -0.62
    eding
    -0.62
    FT
    -0.60
    POSITIVE LOGITS
    ously
    1.11
    netflix
    1.06
     humor
    0.94
     humour
    0.93
     banter
    0.82
     exaggeration
    0.81
     parody
    0.80
    isma
    0.80
    oker
    0.78
     comedic
    0.77
    Activations Density 0.071%

    No Known Activations