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. 11-RES-JB
    6. 4331
    Prev
    Next
    INDEX
    Explanations

    large numerical figures related to populations, sizes, and quantities

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly related to population statistics and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    avascript
    -0.72
     Doct
    -0.68
     inconsistency
    -0.67
     fest
    -0.65
     Clicker
    -0.65
     reluct
    -0.64
    inventoryQuantity
    -0.63
    actionDate
    -0.61
     ARTICLE
    -0.61
     horizont
    -0.60
    POSITIVE LOGITS
     million
    1.82
     billion
    1.72
    million
    1.67
    billion
    1.57
     trillion
    1.56
     lakh
    1.51
     crore
    1.51
     Million
    1.42
     MILL
    1.38
     Billion
    1.35
    Activations Density 0.106%

    No Known Activations