© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13790
    Prev
    Next
    INDEX
    Explanations

    words related to computer interface elements such as menus, toolbar, buttons, and options

    oai_token-act-pair · gpt-3.5-turbo

    items and options related to user interface elements in software applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bred
    -0.87
    breeding
    -0.78
    istani
    -0.75
    fund
    -0.74
    anol
    -0.72
    IVERS
    -0.70
    ETH
    -0.70
    DNA
    -0.70
    utsche
    -0.69
    reb
    -0.67
    POSITIVE LOGITS
     toolbar
    1.20
     pane
    1.18
     popup
    1.16
     widget
    1.15
     scrolling
    1.10
     sidebar
    1.06
     widgets
    1.00
     layout
    1.00
    Widget
    0.99
     navigation
    0.98
    Activations Density 0.121%

    No Known Activations