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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22193
    Prev
    Next
    INDEX
    Explanations

    humorous or funny content

    oai_token-act-pair · gpt-3.5-turbo

    expressions of humor, particularly those related to being funny or hilarious

    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
    Process
    -0.81
     Scale
    -0.76
    Scale
    -0.70
    process
    -0.69
    system
    -0.69
    osph
    -0.69
     atom
    -0.68
     Regions
    -0.68
     properties
    -0.68
    pri
    -0.67
    POSITIVE LOGITS
     hilarious
    3.25
     hilar
    2.41
     humorous
    2.37
     amusing
    2.27
     comedic
    2.03
     funn
    1.96
     funny
    1.88
     witty
    1.82
     sarcastic
    1.68
     satirical
    1.66
    Activations Density 0.042%

    No Known Activations