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. 10-RES-JB
    6. 22669
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences starting with "There."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "There" as a sentence starter or introductory phrase

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comprom
    -0.64
     wheelchair
    -0.56
    natureconservancy
    -0.55
     Throne
    -0.55
    tnc
    -0.54
     Ashes
    -0.53
     IPM
    -0.53
    icial
    -0.53
     notch
    -0.53
     Armored
    -0.53
    POSITIVE LOGITS
    after
    1.50
    upon
    1.46
    abouts
    1.38
    fore
    1.04
    by
    0.97
    FORE
    0.95
     are
    0.92
    for
    0.89
     aren
    0.86
     weren
    0.83
    Activations Density 0.088%

    No Known Activations