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. 0-RES-JB
    6. 17386
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals named Williams

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Williams."

    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
     isot
    -0.69
    fusc
    -0.68
     iod
    -0.67
    mented
    -0.66
    tf
    -0.66
     aval
    -0.65
    MET
    -0.64
    iatric
    -0.64
     ingest
    -0.64
    packs
    -0.64
    POSITIVE LOGITS
     Williams
    3.69
    Williams
    3.03
     Williamson
    1.54
     Watkins
    1.52
     Wright
    1.33
     Greene
    1.32
     Evans
    1.31
     Jennings
    1.30
     Roberts
    1.30
     Jenkins
    1.29
    Activations Density 0.016%

    No Known Activations