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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 5311
    Prev
    Next
    INDEX
    Explanations

    references to comedy or comedic content

    oai_token-act-pair · gpt-3.5-turbo

    references to comedy and comedic content

    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
    ignty
    -0.76
    hips
    -0.74
    eus
    -0.71
     violet
    -0.70
    ports
    -0.69
    ipped
    -0.68
    urion
    -0.66
    EMS
    -0.66
    heed
    -0.66
    tnc
    -0.65
    POSITIVE LOGITS
     improvis
    0.90
     sketches
    0.89
     comedy
    0.88
     Schumer
    0.87
     comedian
    0.87
     comedians
    0.83
     Comedy
    0.83
     Comed
    0.82
     roast
    0.80
     improv
    0.80
    Activations Density 0.060%

    No Known Activations