© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 11255
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions for cooking recipes

    oai_token-act-pair · gpt-3.5-turbo

    food-related ingredients and measurements in recipes

    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
     Interstellar
    -0.82
     exhibitions
    -0.73
     seminars
    -0.70
     Airways
    -0.70
     WC
    -0.69
     simulations
    -0.69
     Clothing
    -0.69
    ersive
    -0.67
     Concert
    -0.67
    MET
    -0.66
    POSITIVE LOGITS
     diced
    1.42
     onions
    1.39
     onion
    1.37
     garlic
    1.34
     peeled
    1.29
     chopped
    1.28
     minced
    1.27
     peppers
    1.25
     tomatoes
    1.24
     carrots
    1.23
    Activations Density 0.112%

    No Known Activations