© 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. 0-RES-JB
    11. 11255
    Prev
    Next
    INDEX
    Explanations

    references to rice

    oai_token-act-pair · gpt-3.5-turbo

    references to rice and its related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    monton
    -0.71
     Stefan
    -0.70
     Finder
    -0.67
     Aston
    -0.66
     Ghostbusters
    -0.66
     Crypt
    -0.66
    Plug
    -0.64
     Vaughn
    -0.63
    Op
    -0.63
    BIT
    -0.62
    POSITIVE LOGITS
     rice
    3.65
     Rice
    2.06
     maize
    1.71
     soy
    1.62
     wheat
    1.58
     barley
    1.58
     noodles
    1.49
     rye
    1.45
     cereal
    1.44
     grains
    1.44
    Activations Density 0.009%

    No Known Activations