Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 4742
    Prev
    Next
    INDEX
    Explanations

    instances of humor or jokes in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "funny" and its variations within the text

    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
    ainer
    -1.01
    ugal
    -0.93
    ership
    -0.86
    ajor
    -0.85
    hent
    -0.78
    agall
    -0.78
    krit
    -0.76
    ignt
    -0.75
    rylic
    -0.75
    hip
    -0.75
    POSITIVE LOGITS
     looking
    0.81
     Guys
    0.80
     sounding
    0.75
     scenes
    0.75
     bone
    0.72
     tale
    0.71
     happen
    0.70
     stories
    0.70
     sauce
    0.69
    ness
    0.69
    Activations Density 0.041%

    No Known Activations