© 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. 1-RES-JB
    11. 10356
    Prev
    Next
    INDEX
    Explanations

    types of grains, specifically focusing on wheat

    oai_token-act-pair · gpt-3.5-turbo

    references to grain, specifically wheat

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ISTER
    -0.89
    href
    -0.80
    isters
    -0.78
    olulu
    -0.68
     reperto
    -0.66
    nels
    -0.65
     Teach
    -0.64
    aphael
    -0.62
    ocket
    -0.62
    ister
    -0.61
    POSITIVE LOGITS
     wheat
    1.13
    grass
    1.05
    weed
    0.98
     gluten
    0.97
    grain
    0.89
     grain
    0.88
     flour
    0.87
    moil
    0.84
     bread
    0.83
     Wheat
    0.82
    Activations Density 0.005%

    No Known Activations