© 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. 8-RES-JB
    11. 9051
    Prev
    Next
    INDEX
    Explanations

    phrases related to labor, workforce, and employment

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with labor and employment issues

    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
    irs
    -0.90
     Flavoring
    -0.76
     Qiao
    -0.75
     Gamble
    -0.75
     Buckingham
    -0.71
     Dak
    -0.68
    romeda
    -0.68
    rah
    -0.65
     Poker
    -0.65
     Bosh
    -0.65
    POSITIVE LOGITS
     unions
    1.03
     labor
    0.93
     stopp
    0.91
    union
    0.89
    iously
    0.87
     union
    0.87
    worker
    0.85
    wage
    0.85
     laborers
    0.83
     aristocracy
    0.79
    Activations Density 0.039%

    No Known Activations