© 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. 12-RES-JB
    11. 5121
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions for a dessert recipe

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    instructions and components related to baking recipes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Reeves
    -1.01
    Xbox
    -0.88
     Chomsky
    -0.85
    Houston
    -0.82
    Dial
    -0.82
    Lev
    -0.81
     Lyndon
    -0.80
     Weld
    -0.80
    vid
    -0.80
     Chargers
    -0.80
    POSITIVE LOGITS
     chocolate
    1.86
     cake
    1.85
     cakes
    1.79
     cookies
    1.71
     dessert
    1.70
    ecake
    1.70
     Cake
    1.66
     icing
    1.66
     Chocolate
    1.64
     pastry
    1.63
    Activations Density 0.320%

    No Known Activations