© 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. 9-RES-JB
    11. 18562
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sauce" with varying degrees of emphasis or description

    oai_token-act-pair · gpt-3.5-turbo

    references to sauces and their preparation 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 @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redit
    -0.72
     WATCHED
    -0.70
    vernment
    -0.70
     Camer
    -0.69
     Borders
    -0.68
    allery
    -0.66
     Schne
    -0.66
     Democr
    -0.65
     Visitors
    -0.62
    agall
    -0.62
    POSITIVE LOGITS
     sauces
    1.19
     sauce
    1.15
    Ingredients
    1.08
     conco
    0.96
    pan
    0.95
    Recipe
    0.95
     seasoning
    0.93
     simmer
    0.92
     ingredients
    0.92
    ming
    0.91
    Activations Density 0.039%

    No Known Activations