© 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. 8-RES-JB
    11. 2627
    Prev
    Next
    INDEX
    Explanations

    references to the word "rice."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of rice

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    istically
    -0.77
    laus
    -0.71
    acular
    -0.69
    ufact
    -0.69
    izons
    -0.68
    atural
    -0.67
    ÑĮ
    -0.67
    */(
    -0.65
    odic
    -0.64
    ãĥĦ
    -0.64
    POSITIVE LOGITS
     cooker
    1.26
    washer
    0.92
     padd
    0.91
    cloth
    0.90
     cakes
    0.90
    beans
    0.88
    cook
    0.84
    bean
    0.83
    bowl
    0.83
     bowls
    0.83
    Activations Density 0.036%

    No Known Activations