© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 5110
    Prev
    Next
    INDEX
    Explanations

    mentions of the web browser Firefox

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Firefox web browser, especially its versions and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rad
    -0.71
    anic
    -0.66
     tant
    -0.65
     trib
    -0.65
     sing
    -0.64
    ettlement
    -0.64
    ti
    -0.64
     sac
    -0.62
    ÃŃs
    -0.62
     plac
    -0.62
    POSITIVE LOGITS
     Firefox
    3.59
     Mozilla
    2.32
     Chrome
    1.72
    browser
    1.56
     browsers
    1.53
     jQuery
    1.49
     Browser
    1.44
     browser
    1.42
     Gmail
    1.37
    Browser
    1.36
    Activations Density 0.014%

    No Known Activations