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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 4584
    Prev
    Next
    INDEX
    Explanations

    phrases related to remuneration and compensation

    oai_token-act-pair · gpt-3.5-turbo

    references to salary and compensation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ells
    -0.78
    Jess
    -0.73
     Twist
    -0.71
    sonian
    -0.68
     Goodwin
    -0.66
     Peb
    -0.66
    alter
    -0.66
     Ange
    -0.66
     Edison
    -0.65
    Berry
    -0.65
    POSITIVE LOGITS
     salary
    1.10
     earners
    1.10
     dues
    0.99
     salaries
    0.97
     compensation
    0.89
     income
    0.88
     Salary
    0.87
     wages
    0.87
     rent
    0.83
     payable
    0.82
    Activations Density 0.018%

    No Known Activations