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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 4435
    Prev
    Next
    INDEX
    Explanations

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

    oai_token-act-pair · gpt-3.5-turbo

    references to wheat and its related products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENA
    -0.81
    agame
    -0.78
    NSA
    -0.78
    FTWARE
    -0.74
    ISTER
    -0.74
    nels
    -0.72
    TION
    -0.70
    EStream
    -0.70
     Cosponsors
    -0.69
    irlf
    -0.69
    POSITIVE LOGITS
    meal
    1.02
     starch
    1.00
     gluten
    0.98
     flour
    0.93
     germ
    0.89
     syrup
    0.88
     flakes
    0.82
    grain
    0.81
    osph
    0.81
    grass
    0.80
    Activations Density 0.029%

    No Known Activations