© 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. 4-RES-JB
    11. 10054
    Prev
    Next
    INDEX
    Explanations

    information related to recipes, including preparation times and ingredient quantities

    oai_token-act-pair · gpt-3.5-turbo

    cooking preparation times and related instructions

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

    No Comments

    Negative Logits
     Ubisoft
    -0.79
     Sega
    -0.78
     Activision
    -0.72
     ISPs
    -0.71
     consoles
    -0.71
     EEG
    -0.71
     Aerospace
    -0.70
     unmanned
    -0.70
     fences
    -0.70
     Telecom
    -0.70
    POSITIVE LOGITS
    Ingredients
    1.42
    Recipe
    1.27
     Ingredients
    1.20
    isine
    1.16
     Recipe
    1.13
     Recipes
    1.06
    Slow
    1.05
    redients
    1.05
     Cooking
    1.04
    ecake
    1.00
    Activations Density 0.211%

    No Known Activations