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. 24199
    Prev
    Next
    INDEX
    Explanations

    file navigation and computer system instructions

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to computer operations and navigation

    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
    oln
    -0.67
    jad
    -0.66
    owe
    -0.66
    aughs
    -0.64
    clus
    -0.62
    istani
    -0.62
     weddings
    -0.61
     perpet
    -0.61
     elephants
    -0.60
     fundra
    -0.60
    POSITIVE LOGITS
     Preferences
    1.06
     folder
    1.04
     ->
    0.96
     shortcut
    0.94
     Settings
    0.94
     menu
    0.92
    Ctrl
    0.90
     >
    0.90
     pane
    0.87
     Folder
    0.86
    Activations Density 0.155%

    No Known Activations