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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23631
    Prev
    Next
    INDEX
    Explanations

    terms related to financial matters specifically relating to payroll

    oai_token-act-pair · gpt-3.5-turbo

    references to payroll

    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
    stan
    -0.81
     Chim
    -0.69
    ge
    -0.65
    ras
    -0.65
    aja
    -0.64
    ori
    -0.63
    aunt
    -0.63
     Dri
    -0.63
    rons
    -0.62
    etus
    -0.62
    POSITIVE LOGITS
     payroll
    4.10
     salary
    1.49
     salaries
    1.46
     paycheck
    1.43
     rosters
    1.23
     Salary
    1.21
     hiring
    1.19
     employer
    1.16
     layoffs
    1.15
     wages
    1.14
    Activations Density 0.006%

    No Known Activations