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. 3138
    Prev
    Next
    INDEX
    Explanations

    common financial terms related to borrowing money, specifically focusing on the concept of loans

    oai_token-act-pair · gpt-3.5-turbo

    references to loans, particularly in a financial or economic context

    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
    MET
    -0.73
    Flag
    -0.72
    visual
    -0.66
    pect
    -0.65
     Ske
    -0.64
    isson
    -0.63
    flag
    -0.62
    Met
    -0.62
     MET
    -0.62
     Terry
    -0.60
    POSITIVE LOGITS
     loans
    3.63
     loan
    2.64
     Loans
    2.57
     Loan
    2.32
     mortgages
    2.32
     lenders
    2.25
     borrowers
    2.10
     debts
    2.05
     lending
    1.92
     lender
    1.91
    Activations Density 0.013%

    No Known Activations