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. 3-RES-JB
    6. 21824
    Prev
    Next
    INDEX
    Explanations

    words related to financial loans and lending

    oai_token-act-pair · gpt-3.5-turbo

    terms related to loans and lending

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMAGES
    -0.77
    inct
    -0.76
     Flavoring
    -0.76
    Tact
    -0.74
     VID
    -0.71
    rics
    -0.69
    ART
    -0.67
    alde
    -0.67
    ++++++++++++++++
    -0.66
    rawdownloadcloneembedreportprint
    -0.66
    POSITIVE LOGITS
     repayment
    1.28
     loans
    1.20
     repay
    1.14
     lender
    1.06
     loan
    1.05
     Loans
    1.01
     repaid
    1.00
     lending
    0.97
     mortgages
    0.94
     lenders
    0.94
    Activations Density 0.018%

    No Known Activations