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. 11-RES-JB
    6. 19665
    Prev
    Next
    INDEX
    Explanations

    mentions of Wi-Fi connectivity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Wi-Fi and related connectivity terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uate
    -0.72
     succeeding
    -0.60
    uations
    -0.60
    ulous
    -0.59
    stall
    -0.59
     McDonnell
    -0.58
     Holt
    -0.58
    lain
    -0.57
     favors
    -0.55
     triumphant
    -0.55
    POSITIVE LOGITS
    Fi
    1.04
    MAX
    0.95
    ener
    0.94
    Max
    0.85
    Wi
    0.85
    etooth
    0.84
    LED
    0.83
     Fi
    0.82
    FI
    0.82
    Pi
    0.79
    Activations Density 0.015%

    No Known Activations