© 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. 10-RES-JB
    11. 10570
    Prev
    Next
    INDEX
    Explanations

    information related to layoffs and employee cuts in various companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    information about job losses and layoffs in companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fml
    -0.73
     Conspiracy
    -0.69
    jac
    -0.68
    json
    -0.67
    é»Ĵ
    -0.67
    aband
    -0.64
    heid
    -0.64
    eteenth
    -0.64
     suspic
    -0.64
     revolutions
    -0.63
    POSITIVE LOGITS
     layoffs
    1.47
     workforce
    1.47
     redund
    1.35
     staffing
    1.28
     jobs
    1.24
     hires
    1.24
     employees
    1.20
     redundant
    1.16
     staff
    1.16
     payroll
    1.15
    Activations Density 0.340%

    No Known Activations