© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 3072
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions in a recipe

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gund
    -0.80
    quest
    -0.77
     Nanto
    -0.74
     diagn
    -0.73
     EEG
    -0.71
     Vale
    -0.67
     trades
    -0.67
     partName
    -0.67
    Corp
    -0.67
     patrols
    -0.67
    POSITIVE LOGITS
     sweetness
    1.15
     creamy
    1.12
     texture
    1.11
     sauces
    1.08
     crispy
    1.08
    Ingredients
    1.04
     crust
    1.01
     flavorful
    1.01
     pastry
    1.01
     caramel
    1.01
    Activations Density 0.152%

    No Known Activations