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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-RES-JB
    6. 23714
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of soups

    oai_token-act-pair · gpt-3.5-turbo

    references to soup and broth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oral
    -0.70
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.65
    inel
    -0.65
     Knight
    -0.64
    uate
    -0.64
     Hobby
    -0.63
     Freem
    -0.62
    phas
    -0.61
    sburg
    -0.61
     arresting
    -0.61
    POSITIVE LOGITS
     soup
    1.48
     Soup
    1.37
    bowl
    1.00
     kitchens
    0.97
     broth
    0.93
     nood
    0.91
     sou
    0.86
     bowls
    0.86
     bowl
    0.85
    ée
    0.82
    Activations Density 0.006%

    No Known Activations