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. 3-RES-JB
    6. 14980
    Prev
    Next
    INDEX
    Explanations

    phrases related to broadband internet services

    oai_token-act-pair · gpt-3.5-turbo

    references to broadband internet

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hiro
    -0.79
     Bie
    -0.75
    urat
    -0.71
    venge
    -0.71
    udic
    -0.70
    ammad
    -0.70
    orian
    -0.69
    ean
    -0.69
    qt
    -0.68
    pha
    -0.66
    POSITIVE LOGITS
     broadband
    1.04
     connectivity
    1.03
     providers
    0.87
     subscriber
    0.85
     speeds
    0.85
     subscribers
    0.83
    rastructure
    0.80
     infrastructure
    0.79
     provider
    0.78
     networks
    0.76
    Activations Density 0.008%

    No Known Activations