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. 7-RES-JB
    6. 24235
    Prev
    Next
    INDEX
    Explanations

    the interjection "um" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    filler words and interjections often used in spoken language

    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
    hire
    -0.65
     rendered
    -0.64
    ingham
    -0.64
    BOOK
    -0.63
    ttes
    -0.61
     Stevenson
    -0.61
    hips
    -0.60
    女
    -0.60
    Constructed
    -0.59
    ebook
    -0.59
    POSITIVE LOGITS
    pty
    1.04
    rah
    0.93
    br
    0.88
    ming
    0.88
    pling
    0.87
    iven
    0.86
    yssey
    0.86
    ihara
    0.84
    amoto
    0.84
    ugh
    0.83
    Activations Density 0.029%

    No Known Activations