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. 10843
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named Thompson

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Thompson"

    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
     Emir
    -0.85
     maid
    -0.78
    rones
    -0.75
     Aer
    -0.70
     clouds
    -0.67
     Rub
    -0.67
    Cloud
    -0.67
     corp
    -0.65
     decree
    -0.64
     UAE
    -0.64
    POSITIVE LOGITS
     Thompson
    3.79
    Thompson
    3.15
     Thomson
    1.55
     Stephenson
    1.42
    Thom
    1.30
     Thornton
    1.29
     Livingston
    1.28
     Kerr
    1.28
     Thom
    1.26
     Barnes
    1.22
    Activations Density 0.014%

    No Known Activations