Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 14799
    Prev
    Next
    INDEX
    Explanations

    mentions of various types of recipes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sachs
    -0.70
    Wil
    -0.70
     Pall
    -0.69
    chester
    -0.67
     Disability
    -0.67
     Bermuda
    -0.66
     Citizens
    -0.66
     Zurich
    -0.64
     VG
    -0.64
     Ace
    -0.63
    POSITIVE LOGITS
     recipes
    1.48
     Recipes
    1.16
     recip
    1.13
     recipe
    1.10
    poons
    1.04
    Recipe
    1.00
    isine
    0.98
     menus
    0.94
     sauces
    0.92
    poon
    0.91
    Activations Density 0.009%

    No Known Activations