© 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. 1250
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of workers

    oai_token-act-pair · gpt-3.5-turbo

    references to workers and labor-related themes

    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
     Hayden
    -0.74
    bang
    -0.67
    ebook
    -0.67
    format
    -0.66
    gie
    -0.66
    rex
    -0.63
    nit
    -0.62
    tone
    -0.61
    ogue
    -0.61
     Imper
    -0.60
    POSITIVE LOGITS
     workers
    3.55
     worker
    2.86
     Workers
    2.76
    workers
    2.73
     laborers
    2.34
     Worker
    2.32
     employees
    2.29
    worker
    2.24
     labou
    1.95
     Employees
    1.88
    Activations Density 0.033%

    No Known Activations