© 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. 8-RES-JB
    11. 22299
    Prev
    Next
    INDEX
    Explanations

    terms related to internet browsers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "browser" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lakes
    -0.74
    seeking
    -0.73
    egal
    -0.73
    orian
    -0.69
    ioxide
    -0.68
     Swanson
    -0.68
    von
    -0.68
    bringer
    -0.67
    ional
    -0.65
    enser
    -0.65
    POSITIVE LOGITS
     toolbar
    1.03
     browsers
    0.88
    browser
    0.87
     browser
    0.87
     plugins
    0.85
     interface
    0.82
    oad
    0.82
     Browser
    0.81
     plugin
    0.79
    olson
    0.77
    Activations Density 0.038%

    No Known Activations