© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 15755
    Prev
    Next
    INDEX
    Explanations

    phrases related to humor or comedy

    oai_token-act-pair · gpt-3.5-turbo

    instances of humor or the concept of being funny

    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
    aido
    -0.75
    ansion
    -0.74
    idis
    -0.72
    borough
    -0.67
     determines
    -0.64
     Ensure
    -0.63
    Aid
    -0.62
    monitor
    -0.62
     Init
    -0.62
     Prepar
    -0.61
    POSITIVE LOGITS
     funny
    3.39
     hilarious
    2.26
     Funny
    2.13
     humorous
    2.00
     funn
    1.96
     amusing
    1.86
     witty
    1.77
     humor
    1.64
     comedic
    1.60
     humour
    1.57
    Activations Density 0.008%

    No Known Activations