© 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. 10-RES-JB
    11. 13813
    Prev
    Next
    INDEX
    Explanations

    names of company executives

    oai_token-act-pair · gpt-3.5-turbo

    references to prominent company executives and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CVE
    -0.73
     wounding
    -0.69
     curfew
    -0.68
    jury
    -0.68
     Rebels
    -0.66
    tackle
    -0.65
    violence
    -0.64
     SCHOOL
    -0.64
     queens
    -0.63
     filib
    -0.63
    POSITIVE LOGITS
    CEO
    1.04
     Ventures
    0.94
     Lei
    0.88
     Bezos
    0.88
     IPO
    0.88
     Investment
    0.88
     shareholders
    0.87
     Kaplan
    0.87
     Wein
    0.86
     Acquisition
    0.86
    Activations Density 0.145%

    No Known Activations