Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9699
    Prev
    Next
    INDEX
    Explanations

    words related to regulations and restrictions in a context of urban planning or technology infrastructure

    oai_token-act-pair · gpt-3.5-turbo

    specific references to regulations or restrictions related to broadband and internet services

    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
     perfume
    -0.94
    iazep
    -0.90
     fragrance
    -0.89
    borgh
    -0.84
     Suarez
    -0.82
    jew
    -0.82
     Yaz
    -0.80
    nesty
    -0.80
    Naz
    -0.78
    wcsstore
    -0.78
    POSITIVE LOGITS
     broadband
    1.86
     NBN
    1.86
     ISPs
    1.70
     fibre
    1.68
     Fiber
    1.63
     ISP
    1.62
     Comcast
    1.60
     Cable
    1.58
     Mbps
    1.48
     DSL
    1.45
    Activations Density 0.380%

    No Known Activations