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. 9-RES-JB
    6. 22226
    Prev
    Next
    INDEX
    Explanations

    the word "just" followed by a number, like a comparison

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "just" in various contexts emphasizing limitations or exclusions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ͻ
    -0.81
    cyclopedia
    -0.67
    Dispatch
    -0.64
    gha
    -0.62
    uum
    -0.61
    ero
    -0.61
    ERAL
    -0.60
    +
    -0.59
    Various
    -0.59
    inem
    -0.59
    POSITIVE LOGITS
    lihood
    0.74
     anymore
    0.73
     mention
    0.72
     nor
    0.69
     necessarily
    0.66
    standing
    0.63
     kidding
    0.62
    cause
    0.62
    ches
    0.60
     ours
    0.60
    Activations Density 0.107%

    No Known Activations