© 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. 5025
    Prev
    Next
    INDEX
    Explanations

    ingredients and instructions for preparing recipes

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

    ingredients and components commonly used in cooking and 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
    ä¸ī
    -0.64
     Earthquake
    -0.62
    election
    -0.60
     Opportun
    -0.60
     BlackBerry
    -0.58
     Odyssey
    -0.58
     Greenberg
    -0.57
     Passage
    -0.56
     Heard
    -0.55
     Ride
    -0.55
    POSITIVE LOGITS
     starch
    1.06
     broth
    0.98
     flour
    0.93
     powder
    0.93
     pulp
    0.92
     flakes
    0.91
     vinegar
    0.91
     mixture
    0.90
     juice
    0.89
     grease
    0.86
    Activations Density 0.120%

    No Known Activations