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

    Neuronpedia

    APICircuit 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. 22680
    Prev
    Next
    INDEX
    Explanations

    references to the former US President George W. Bush

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "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
    pmwiki
    -0.71
    ãĤ©
    -0.70
     ancest
    -0.68
    £ı
    -0.68
    adobe
    -0.67
    »Ĵ
    -0.61
     complementary
    -0.60
     tracker
    -0.59
    BUT
    -0.59
    Ont
    -0.59
    POSITIVE LOGITS
     Bush
    1.15
    .,
    1.09
    .,"
    1.01
    .),
    0.92
    .;
    0.91
    Bush
    0.89
    .?
    0.86
    ulf
    0.84
    .).
    0.84
     Abrams
    0.82
    Activations Density 0.014%

    No Known Activations