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. 0-RES-JB
    6. 8541
    Prev
    Next
    INDEX
    Explanations

    references to Internet Service Providers (ISPs)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Internet Service Providers (ISPs) and related network terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decorated
    -0.80
    reciation
    -0.78
     ger
    -0.72
     rust
    -0.71
    rose
    -0.70
     ceremonial
    -0.69
    condition
    -0.69
     rapt
    -0.69
     hol
    -0.67
     golden
    -0.67
    POSITIVE LOGITS
     ISPs
    3.44
     ISP
    3.36
     VPN
    1.71
    VPN
    1.41
     DNS
    1.32
     NBN
    1.31
     Mbps
    1.30
     routers
    1.22
     broadband
    1.22
     insurers
    1.21
    Activations Density 0.019%

    No Known Activations