© 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. 19308
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "startup" in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to startups

    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
    deen
    -0.72
     Ple
    -0.72
    lor
    -0.72
    ylum
    -0.67
     Poc
    -0.66
    bons
    -0.65
    çİĭ
    -0.65
    orical
    -0.63
     clothed
    -0.63
     Eug
    -0.62
    POSITIVE LOGITS
     startup
    3.74
     Startup
    2.90
     startups
    2.58
     entrepreneurship
    1.41
     entrepreneurial
    1.29
     entrepreneurs
    1.27
     entrepreneur
    1.27
     initialization
    1.23
     tech
    1.22
     VC
    1.17
    Activations Density 0.025%

    No Known Activations