© 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. 20803
    Prev
    Next
    INDEX
    Explanations

    instructions or mentions about making food or recipes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to cooking and food preparation instructions

    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
    Privacy
    -0.90
    Politics
    -0.81
    Film
    -0.80
    Plot
    -0.78
    Financial
    -0.77
    pmwiki
    -0.77
    Tele
    -0.77
    Voice
    -0.77
    Media
    -0.75
     Telecommunications
    -0.75
    POSITIVE LOGITS
     roasted
    1.51
     spinach
    1.46
     grilled
    1.44
     tofu
    1.43
     garlic
    1.41
     coconut
    1.41
     broccoli
    1.41
     kale
    1.39
     avocado
    1.39
     homemade
    1.37
    Activations Density 0.238%

    No Known Activations