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. 1-RES-JB
    6. 19060
    Prev
    Next
    INDEX
    Explanations

    information related to wages and payment in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to wages and their implications in the workplace and economy

    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
    OPS
    -0.72
    \/\/
    -0.69
    DEP
    -0.69
    ergy
    -0.67
    ocl
    -0.66
     Blossom
    -0.65
    design
    -0.64
    ----------
    -0.63
     Jub
    -0.62
     Greene
    -0.61
    POSITIVE LOGITS
     wages
    1.20
     earners
    1.08
     wage
    0.89
    chwitz
    0.88
    wage
    0.88
     ($)
    0.87
     Wage
    0.85
    payer
    0.82
     incomes
    0.82
     rents
    0.81
    Activations Density 0.007%

    No Known Activations