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. 10-RES-JB
    6. 14609
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "chopped" and its variations in cooking instructions

    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
    ruck
    -0.78
    agents
    -0.77
    soDeliveryDate
    -0.75
    rences
    -0.71
    HUD
    -0.71
     Monitoring
    -0.70
    externalActionCode
    -0.69
    Charges
    -0.68
    ggles
    -0.68
    BAT
    -0.68
    POSITIVE LOGITS
     onions
    1.08
     slices
    0.98
     onion
    0.96
     vegetables
    0.91
    aneous
    0.91
     cabbage
    0.89
     chop
    0.88
     carrots
    0.85
     chunks
    0.84
     veggies
    0.84
    Activations Density 0.060%

    No Known Activations