© 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. 5085
    Prev
    Next
    INDEX
    Explanations

    baking instructions and ingredients

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

    keywords related to baking and cooking processes

    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
     Levi
    -0.61
    igators
    -0.58
     Investigative
    -0.58
     Kelley
    -0.57
    ryu
    -0.56
    aterasu
    -0.56
    age
    -0.56
     Guitar
    -0.56
    ality
    -0.55
     Cardinal
    -0.55
    POSITIVE LOGITS
     soda
    1.19
    lite
    0.91
     powder
    0.88
     parchment
    0.86
     chall
    0.79
     oats
    0.72
     dish
    0.71
    rouch
    0.70
     Soda
    0.69
     cider
    0.69
    Activations Density 0.043%

    No Known Activations