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. 24560
    Prev
    Next
    INDEX
    Explanations

    mentions of the financial instrument 'stock'

    oai_token-act-pair · gpt-3.5-turbo

    references to stocks and stock market terminology

    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
    interstitial
    -0.74
    uth
    -0.68
    iquette
    -0.66
    »
    -0.66
    urally
    -0.65
    heim
    -0.65
    olith
    -0.63
    ouri
    -0.63
     Geh
    -0.63
     interpre
    -0.62
    POSITIVE LOGITS
     stock
    4.04
    stock
    2.69
     Stock
    2.68
     stocks
    2.56
    Stock
    2.52
    stocks
    2.34
     stocking
    1.54
     shares
    1.30
     securities
    1.27
     shareholder
    1.23
    Activations Density 0.011%

    No Known Activations