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. 1-RES-JB
    6. 16629
    Prev
    Next
    INDEX
    Explanations

    terms related to internet browsing and online activities

    oai_token-act-pair · gpt-3.5-turbo

    references to web browsing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rum
    -0.74
    si
    -0.61
    Te
    -0.60
     pronounced
    -0.60
    reek
    -0.60
    lain
    -0.60
     Lauder
    -0.60
    hips
    -0.59
     Lakes
    -0.59
    ENCY
    -0.59
    POSITIVE LOGITS
     browsing
    1.32
     browse
    1.04
    ãĤ¦ãĤ¹
    0.91
     Browse
    0.88
    oad
    0.83
    76561
    0.80
     surfing
    0.77
     "$:/
    0.77
     sessions
    0.76
    Īè
    0.75
    Activations Density 0.012%

    No Known Activations