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. 16800
    Prev
    Next
    INDEX
    Explanations

    requests for selection or input with specific options

    oai_token-act-pair · gpt-3.5-turbo

    requests for user inputs related to selecting options

    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
    hran
    -0.80
     eaves
    -0.64
    albeit
    -0.64
    ppard
    -0.63
    still
    -0.63
     meanwhile
    -0.63
    forth
    -0.62
    withstanding
    -0.62
     intrins
    -0.62
     ener
    -0.60
    POSITIVE LOGITS
     Select
    1.08
     Choose
    1.00
     Submit
    0.98
     Sort
    0.93
     {*
    0.91
     Cancel
    0.90
     Description
    0.89
     Seller
    0.88
     Category
    0.88
     Search
    0.87
    Activations Density 0.187%

    No Known Activations