© 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. 20492
    Prev
    Next
    INDEX
    Explanations

    mentions of salaries or salary-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to salary figures and compensation

    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
    ooks
    -0.72
    warts
    -0.64
    emon
    -0.64
     Encounter
    -0.63
    Craft
    -0.61
    worms
    -0.61
    wart
    -0.61
    UU
    -0.61
    VERS
    -0.60
     gripped
    -0.59
    POSITIVE LOGITS
     salary
    3.61
     Salary
    2.88
     salaries
    2.66
     paycheck
    1.95
     payroll
    1.83
     wage
    1.73
     wages
    1.71
     Wage
    1.45
     earnings
    1.41
     income
    1.40
    Activations Density 0.011%

    No Known Activations