© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 10415
    Prev
    Next
    INDEX
    Explanations

    mentions of financial institutions or individuals associated with financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to lending and borrowers in financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ald
    -0.87
     Offensive
    -0.75
    inct
    -0.70
    ++++++++++++++++
    -0.67
     Neurolog
    -0.67
    ALD
    -0.65
     MacArthur
    -0.64
    neum
    -0.63
     Flavoring
    -0.63
    Copyright
    -0.62
    POSITIVE LOGITS
     lender
    1.39
     lenders
    1.26
     lending
    1.11
     loan
    1.07
     borrower
    1.04
     borrowers
    1.04
     repaid
    1.02
     loans
    1.01
     repayment
    0.98
     repay
    0.92
    Activations Density 0.011%

    No Known Activations