© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18540
    Prev
    Next
    INDEX
    Explanations

    information related to founders of companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals who hold the title of "founder."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alle
    -0.71
    awks
    -0.69
    anche
    -0.67
    oles
    -0.65
    ascar
    -0.63
    ureau
    -0.63
    ascus
    -0.63
    awk
    -0.63
    vor
    -0.63
    perature
    -0.63
    POSITIVE LOGITS
     Ezra
    0.92
    founder
    0.85
     founder
    0.79
     emer
    0.77
     Founder
    0.73
     laureate
    0.73
    lisher
    0.73
    ãĥ¼ãĥĨãĤ£
    0.72
     Andrew
    0.71
     Pavel
    0.70
    Activations Density 0.016%

    No Known Activations