Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 20885
    Prev
    Next
    INDEX
    Explanations

    the name "George W. Bush"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "George," specifically in the context of George W. Bush

    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
    Ranked
    -0.72
    nir
    -0.70
    eers
    -0.68
    places
    -0.68
    lain
    -0.68
     inhibitor
    -0.66
    mble
    -0.66
    utions
    -0.66
    ateral
    -0.66
     crawl
    -0.65
    POSITIVE LOGITS
     Orwell
    1.10
     Soros
    1.06
     Clo
    0.97
     Zimmerman
    0.95
     Bush
    0.91
     Lucas
    0.89
     Osborne
    0.87
     Washington
    0.86
     Herbert
    0.84
     Wallace
    0.84
    Activations Density 0.022%

    No Known Activations