© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 15735
    Prev
    Next
    INDEX
    Explanations

    words related to gluten and grains, particularly wheat, barley, and rye

    oai_token-act-pair · gpt-3.5-turbo

    references to gluten and wheat-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctions
    -0.80
     Gadget
    -0.74
    xes
    -0.73
    CLASSIFIED
    -0.72
     Reno
    -0.70
     Hawth
    -0.68
    Team
    -0.68
    cffffcc
    -0.67
    erial
    -0.66
    ENA
    -0.66
    POSITIVE LOGITS
     gluten
    1.25
     flour
    1.15
     starch
    1.14
     grains
    1.11
    grain
    1.07
    meal
    1.06
     grain
    1.02
     cereal
    1.00
     flakes
    0.97
     germ
    0.97
    Activations Density 0.073%

    No Known Activations