© 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. 8109
    Prev
    Next
    INDEX
    Explanations

    mentions of entrepreneurs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to entrepreneurs and entrepreneurial activity

    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
    ata
    -0.79
    raw
    -0.77
    raph
    -0.72
    graded
    -0.67
    hide
    -0.65
     gore
    -0.64
     Mori
    -0.64
     Trident
    -0.63
     lig
    -0.62
     Uniform
    -0.62
    POSITIVE LOGITS
     entrepreneurs
    3.11
     Entreprene
    2.93
     entrepreneur
    2.92
     entrepreneurship
    2.86
    reprene
    2.56
     entrepreneurial
    2.55
     startups
    2.05
     entreprene
    1.76
     Startup
    1.66
     businessmen
    1.61
    Activations Density 0.021%

    No Known Activations