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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24162
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions related to earning money

    oai_token-act-pair · gpt-3.5-turbo

    terms related to earnings and financial transactions, particularly focusing on paydays and paycheck-related concepts

    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
    ivity
    -0.84
    ive
    -0.83
    eq
    -0.83
    ald
    -0.80
    lim
    -0.80
    atorial
    -0.75
    hip
    -0.75
    iveness
    -0.74
    ively
    -0.74
    lee
    -0.72
    POSITIVE LOGITS
     payday
    1.34
     lender
    1.14
     lenders
    0.98
    soDeliveryDate
    0.88
     Skydragon
    0.85
     expiration
    0.84
     lending
    0.82
     loan
    0.82
     Loan
    0.79
     loans
    0.77
    Activations Density 0.003%

    No Known Activations