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. 12-RES-JB
    6. 15169
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking techniques related to a specific cuisine

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words associated with different types of food or culinary ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     behavi
    -0.93
     exha
    -0.91
     unforeseen
    -0.88
     redes
    -0.80
    CLASSIFIED
    -0.80
     warr
    -0.80
     bottleneck
    -0.80
     departure
    -0.79
     recurring
    -0.78
     conflic
    -0.76
    POSITIVE LOGITS
    ilies
    1.47
    ives
    1.41
    ocol
    1.36
    owder
    1.34
    iles
    1.29
    unky
    1.29
    oux
    1.22
    ardon
    1.19
    ocolate
    1.17
    ai
    1.17
    Activations Density 0.059%

    No Known Activations