© 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. 14195
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions in a recipe

    oai_token-act-pair · gpt-3.5-turbo

    terms related to food ingredients and their preparation methods

    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
     partName
    -0.81
    ļé
    -0.81
    ITNESS
    -0.80
    GBT
    -0.76
    Reviewer
    -0.74
     Bryce
    -0.74
     Polk
    -0.74
    eatures
    -0.73
    EGIN
    -0.73
    RAG
    -0.71
    POSITIVE LOGITS
     syrup
    1.20
     mustard
    1.15
     biscuits
    1.14
     berries
    1.13
     powder
    1.12
     glands
    1.08
     coated
    1.08
    seed
    1.08
     coating
    1.06
     baths
    1.06
    Activations Density 0.275%

    No Known Activations