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. 114
    Prev
    Next
    INDEX
    Explanations

    mentions of kitchen-related items and actions, particularly dishes

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of dishes or meals

    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
    redits
    -0.86
    uminati
    -0.82
    yrights
    -0.75
    ern
    -0.71
     conventions
    -0.69
    started
    -0.68
    BG
    -0.66
     Merrill
    -0.65
    aug
    -0.65
    grounds
    -0.63
    POSITIVE LOGITS
     dish
    3.96
     dishes
    3.01
     Dish
    2.10
     cuisine
    1.42
     meal
    1.26
     salad
    1.17
     culinary
    1.16
     plate
    1.14
     recipe
    1.14
     chef
    1.13
    Activations Density 0.012%

    No Known Activations