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. 11-RES-JB
    6. 10092
    Prev
    Next
    INDEX
    Explanations

    ingredients commonly found in sandwiches and dishes

    oai_token-act-pair · gpt-3.5-turbo

    food items and ingredients in a recipe context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    catentry
    -0.83
    OPLE
    -0.80
    Phones
    -0.75
    Discuss
    -0.74
    dayName
    -0.72
    profit
    -0.69
     Gamergate
    -0.67
    Issue
    -0.66
    YP
    -0.66
    Catalog
    -0.65
    POSITIVE LOGITS
     avocado
    1.37
     onions
    1.33
     veggies
    1.33
     spices
    1.31
     garlic
    1.31
     tomato
    1.29
     gravy
    1.26
     roasted
    1.25
     salsa
    1.25
     cheese
    1.25
    Activations Density 0.110%

    No Known Activations