© 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. 8-RES-JB
    11. 12400
    Prev
    Next
    INDEX
    Explanations

    ingredients and measurements in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    measurements and quantities related to cooking ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Halls
    -0.77
     skelet
    -0.76
    suits
    -0.75
    vironments
    -0.73
     halls
    -0.73
    frames
    -0.71
    models
    -0.68
     Models
    -0.68
     Jenner
    -0.68
    projects
    -0.67
    POSITIVE LOGITS
     tsp
    1.09
     garlic
    1.04
     baking
    1.01
     cinnamon
    0.98
     Flavoring
    0.98
     teaspoon
    0.98
     teaspoons
    0.96
     vinegar
    0.94
     seasoning
    0.93
     iod
    0.92
    Activations Density 0.044%

    No Known Activations