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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 1030
    Prev
    Next
    INDEX
    Explanations

    terms related to internet traffic and online activity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of internet traffic statistics

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

    No Comments

    Negative Logits
    sonian
    -0.98
    lain
    -0.79
    nai
    -0.77
    addons
    -0.75
    arian
    -0.73
    arist
    -0.71
    arine
    -0.71
    ric
    -0.71
     Judith
    -0.69
    humane
    -0.68
    POSITIVE LOGITS
     congestion
    1.04
     jams
    1.01
     flow
    0.96
     flows
    0.90
    flow
    0.85
     traffic
    0.84
     streams
    0.79
     routing
    0.78
     flowing
    0.77
    mails
    0.72
    Activations Density 0.009%

    No Known Activations