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. 136
    Prev
    Next
    INDEX
    Explanations

    instructions for baking recipes, focusing on temperature settings and cooking times

    oai_token-act-pair · gpt-3.5-turbo

    cooking instructions and measurements

    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
    href
    -0.62
     Pf
    -0.62
    Filename
    -0.60
     '[
    -0.60
     headlined
    -0.60
     Yar
    -0.59
     Samar
    -0.59
     Honda
    -0.58
    abase
    -0.58
    pak
    -0.58
    POSITIVE LOGITS
    Remove
    0.87
    Optional
    0.86
    riger
    0.85
     rehe
    0.83
     cooling
    0.83
    optional
    0.80
     Serve
    0.80
     refriger
    0.78
     Nutrition
    0.78
     stirring
    0.77
    Activations Density 0.069%

    No Known Activations