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. 18072
    Prev
    Next
    INDEX
    Explanations

    mentions of internet connection speeds

    oai_token-act-pair · gpt-3.5-turbo

    references to high-speed internet services and broadband plans

    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
     Painter
    -0.85
     perfume
    -0.85
     fragrance
    -0.84
     Scher
    -0.80
    Pain
    -0.78
     cosmetics
    -0.78
    iazep
    -0.74
    pain
    -0.73
     Patri
    -0.72
    othe
    -0.72
    POSITIVE LOGITS
     Mbps
    1.76
    Mbps
    1.74
     broadband
    1.66
     LTE
    1.62
    bps
    1.53
     bandwidth
    1.53
     Ethernet
    1.49
     speeds
    1.45
     modem
    1.41
     WiFi
    1.40
    Activations Density 0.283%

    No Known Activations