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

    Neuronpedia

    Jacobian LensNEW
    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. 8-RES-JB
    11. 21704
    Prev
    Next
    INDEX
    Explanations

    phrases related to employment and financial transactions

    oai_token-act-pair · gpt-3.5-turbo

    references to paid employment or financial compensation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ierre
    -0.97
    ively
    -0.88
     Strait
    -0.77
    âĸ¬
    -0.75
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    iveness
    -0.75
    oys
    -0.73
    _>
    -0.72
    istics
    -0.70
    ARGET
    -0.69
    POSITIVE LOGITS
     dividends
    0.97
     overtime
    0.85
     indemn
    0.85
     invoice
    0.83
     tribute
    0.82
     payroll
    0.82
    ume
    0.82
     subscription
    0.82
     salaries
    0.81
     royalties
    0.81
    Activations Density 0.040%

    No Known Activations