Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 9373
    Prev
    Next
    INDEX
    Explanations

    mentions of various ways of cooking potatoes, including mashed, diced, and fried varieties

    oai_token-act-pair · gpt-3.5-turbo

    references to potatoes

    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
     ED
    -0.74
     Advisory
    -0.72
    eph
    -0.68
    icial
    -0.67
     TC
    -0.64
     Hier
    -0.62
    MT
    -0.62
    Center
    -0.62
    PD
    -0.62
    Ill
    -0.62
    POSITIVE LOGITS
     potatoes
    3.71
     potato
    3.15
     Potato
    2.42
     fries
    1.83
     peas
    1.60
     tomatoes
    1.57
     onions
    1.56
     cabbage
    1.52
    atoes
    1.48
     vegetables
    1.46
    Activations Density 0.018%

    No Known Activations