Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 1-RES-JB
    6. 1816
    Prev
    Next
    INDEX
    Explanations

    mentions of loan-related terms and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "loan" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å°Ĩ
    -0.74
    rics
    -0.74
    anny
    -0.71
    awk
    -0.68
    pire
    -0.68
    atters
    -0.67
    Tact
    -0.67
    Temperature
    -0.67
    addock
    -0.66
     FANTASY
    -0.66
    POSITIVE LOGITS
     loan
    1.27
     repayment
    1.24
     loans
    1.20
     repay
    1.03
     Loan
    1.01
    gage
    0.99
     lender
    0.96
     repaid
    0.95
     lending
    0.94
     borrowers
    0.91
    Activations Density 0.008%

    No Known Activations