© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14149
    Prev
    Next
    INDEX
    Explanations

    ingredients in recipes

    oai_token-act-pair · gpt-3.5-turbo

    references to recipes and food preparation

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Gamergate
    -0.83
     Journals
    -0.78
     scans
    -0.77
     Activision
    -0.72
     seism
    -0.72
     examiner
    -0.71
     diagn
    -0.69
     scan
    -0.69
     Aerospace
    -0.68
     CLS
    -0.68
    POSITIVE LOGITS
    Ingredients
    1.35
     roasted
    1.34
     Recipe
    1.33
     grilled
    1.30
     pasta
    1.27
     Ingredients
    1.26
    iflower
    1.25
     recipe
    1.25
     veggies
    1.24
    Recipe
    1.24
    Activations Density 0.755%

    No Known Activations