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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 14952
    Prev
    Next
    INDEX
    Explanations

    references to the founders of companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "founders" in various contexts

    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
    oute
    -0.71
    ........
    -0.67
     Hazard
    -0.64
    rol
    -0.63
    rated
    -0.62
    ass
    -0.62
    ulation
    -0.61
    liv
    -0.61
     Category
    -0.60
     mode
    -0.59
    POSITIVE LOGITS
     founders
    3.72
     Founders
    2.63
     founding
    1.97
     Founding
    1.93
     founder
    1.84
     Founder
    1.75
     creators
    1.60
     pioneers
    1.57
     entrepreneurs
    1.46
    founder
    1.40
    Activations Density 0.013%

    No Known Activations