© 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. 10-RES-JB
    11. 20502
    Prev
    Next
    INDEX
    Explanations

    verbs related to food preparation

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to cooking or baking processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.71
    href
    -0.65
    alloc
    -0.63
    anmar
    -0.63
    conom
    -0.62
    furt
    -0.61
    SEE
    -0.61
     Reloaded
    -0.61
    âĹ¼
    -0.60
    VID
    -0.60
    POSITIVE LOGITS
     remaining
    0.87
     oven
    0.85
     skillet
    0.83
     mixture
    0.83
    glomer
    0.79
    semble
    0.77
     lid
    0.74
     evenly
    0.74
     Tables
    0.73
    olate
    0.73
    Activations Density 0.094%

    No Known Activations