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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 5978
    Prev
    Next
    INDEX
    Explanations

    recipe ingredients and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    references to food items or recipes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     regress
    -1.01
     reper
    -0.95
     elig
    -0.93
     reckoning
    -0.90
     depreciation
    -0.90
     parity
    -0.89
     veter
    -0.88
     exper
    -0.87
     deliber
    -0.86
     simultane
    -0.85
    POSITIVE LOGITS
     Cream
    1.64
     Cake
    1.62
     Cheese
    1.60
     Smooth
    1.56
     Cookies
    1.55
     Chocolate
    1.54
     Sauce
    1.54
     Salad
    1.53
     Pumpkin
    1.52
     Tomato
    1.50
    Activations Density 0.222%

    No Known Activations