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. 8-RES-JB
    6. 22029
    Prev
    Next
    INDEX
    Explanations

    a recipe or ingredient list in a specific format with quantities and units

    oai_token-act-pair · gpt-3.5-turbo

    measurements and quantities typically used in recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rave
    -0.74
    ivism
    -0.71
    successfully
    -0.69
    assetsadobe
    -0.67
    fm
    -0.65
    alloc
    -0.64
    eve
    -0.63
    idays
    -0.63
    detail
    -0.63
    funded
    -0.62
    POSITIVE LOGITS
     cloves
    1.15
     teasp
    1.14
    ½
    1.12
     tsp
    1.10
     teaspoon
    1.05
     tablespoon
    1.02
     teaspoons
    0.99
     tablespoons
    0.98
     tbsp
    0.96
     garlic
    0.96
    Activations Density 0.062%

    No Known Activations