© 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. 6-RES-JB
    11. 20497
    Prev
    Next
    INDEX
    Explanations

    recipes and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    numerical information related to recipes and cooking times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ejected
    -0.69
    xon
    -0.68
     thereto
    -0.67
     fences
    -0.66
    nesty
    -0.64
    ibur
    -0.64
     towed
    -0.63
     tram
    -0.61
     eject
    -0.61
    dfx
    -0.61
    POSITIVE LOGITS
    Ingredients
    1.02
    isine
    0.99
     Ingredients
    0.97
     Vegan
    0.92
    Recipe
    0.90
     Recipe
    0.86
    Assembly
    0.86
    Method
    0.81
     baking
    0.80
    Slow
    0.79
    Activations Density 0.107%

    No Known Activations