© 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. 0-RES-JB
    11. 16679
    Prev
    Next
    INDEX
    Explanations

    mentions of different aspects of labor, including labor rights, labor disputes, exploitation of labor, and labor market

    oai_token-act-pair · gpt-3.5-turbo

    references to labor and labor rights

    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
    colored
    -0.72
     Cloak
    -0.69
    classic
    -0.67
     Trey
    -0.66
     Cosmic
    -0.65
    onym
    -0.64
    Patch
    -0.63
     Ridge
    -0.63
    lined
    -0.63
    ideshow
    -0.62
    POSITIVE LOGITS
     labour
    4.13
     labor
    3.00
     labou
    2.33
     Labor
    1.68
    Labor
    1.66
    Labour
    1.65
     laborers
    1.61
     Labour
    1.59
     workforce
    1.39
     endeavour
    1.30
    Activations Density 0.014%

    No Known Activations