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. 3-RES-JB
    6. 7710
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "comedy" or "edy."

    oai_token-act-pair · gpt-3.5-turbo

    words and concepts related to comedy and humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    accompan
    -0.90
    ippi
    -0.76
    fortune
    -0.76
    animous
    -0.75
    ific
    -0.74
    inness
    -0.73
    iago
    -0.73
    aged
    -0.72
    ocked
    -0.71
    orem
    -0.71
    POSITIVE LOGITS
    edy
    0.90
    LINE
    0.78
     Reloaded
    0.72
    ge
    0.66
    lly
    0.63
    nels
    0.63
     Hunts
    0.62
     Bastard
    0.62
     alley
    0.62
     Bang
    0.62
    Activations Density 0.011%

    No Known Activations