© 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. 4-RES-JB
    11. 19548
    Prev
    Next
    INDEX
    Explanations

    references to entrepreneurs and entrepreneurship

    oai_token-act-pair · gpt-3.5-turbo

    terms related to entrepreneurship

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

    No Comments

    Negative Logits
    othy
    -0.71
    shall
    -0.68
    olphins
    -0.67
    ophysical
    -0.67
    HEAD
    -0.67
    etr
    -0.66
     Totem
    -0.65
    ferred
    -0.65
    eping
    -0.65
     Panther
    -0.64
    POSITIVE LOGITS
     entrepreneurship
    1.32
    reprene
    1.31
     entrepreneur
    1.21
     entreprene
    1.16
     entrepreneurs
    1.09
     Entreprene
    1.07
     entrepreneurial
    1.04
     incub
    1.01
     ventures
    0.93
     startups
    0.88
    Activations Density 0.017%

    No Known Activations