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. 0-RES-JB
    6. 19732
    Prev
    Next
    INDEX
    Explanations

    large quantities or amounts of something, specifically in the context of money

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities of people or money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    haus
    -0.69
     Healer
    -0.68
    haw
    -0.67
    etic
    -0.67
     (+
    -0.66
    ender
    -0.66
    bard
    -0.65
    angler
    -0.64
    gha
    -0.64
    ework
    -0.63
    POSITIVE LOGITS
     millions
    3.67
     billions
    3.22
     thousands
    2.67
     trillions
    2.65
     Millions
    2.55
     tens
    2.37
     hundreds
    2.18
     Thousands
    1.81
    Thousands
    1.76
    illions
    1.71
    Activations Density 0.010%

    No Known Activations