© 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. 0-RES-JB
    11. 1157
    Prev
    Next
    INDEX
    Explanations

    terms related to salary or payment, particularly emphasizing a high level of wages

    oai_token-act-pair · gpt-3.5-turbo

    references to wages and pay-related discussions

    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
    jam
    -0.73
    hent
    -0.69
     jam
    -0.65
    omer
    -0.63
    ogue
    -0.63
     Phant
    -0.62
    agle
    -0.62
    aze
    -0.62
    emon
    -0.61
     Gemini
    -0.61
    POSITIVE LOGITS
     wages
    3.68
     wage
    2.48
     Wage
    2.24
    wage
    2.13
     salaries
    2.08
     incomes
    1.94
     rents
    1.63
     salary
    1.61
     pensions
    1.50
     paycheck
    1.48
    Activations Density 0.006%

    No Known Activations