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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14020
    Prev
    Next
    INDEX
    Explanations

    ingredients of food dishes, with a particular focus on condiments and toppings

    oai_token-act-pair · gpt-3.5-turbo

    ingredients and components related to food 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
    Discuss
    -1.00
    imester
    -0.85
    Privacy
    -0.82
    Deal
    -0.81
     Publications
    -0.79
    Invest
    -0.79
    reply
    -0.77
    Phones
    -0.77
    Reilly
    -0.77
    gencies
    -0.75
    POSITIVE LOGITS
     garlic
    1.49
     onions
    1.42
     spices
    1.40
     tomato
    1.39
     lemon
    1.38
     avocado
    1.37
     roasted
    1.36
     coconut
    1.33
     tomatoes
    1.31
     almonds
    1.30
    Activations Density 0.126%

    No Known Activations