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. 2-RES-JB
    6. 19254
    Prev
    Next
    INDEX
    Explanations

    keywords related to internet protocols and technology, with a focus on HTTP and HTTPS

    oai_token-act-pair · gpt-3.5-turbo

    references to HTTP and HTTPS protocols and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolet
    -0.75
    =-=-=-=-
    -0.74
    ________________
    -0.74
    itism
    -0.69
    bery
    -0.68
    cum
    -0.67
    eca
    -0.66
    life
    -0.65
    pard
    -0.65
    ________________________
    -0.65
    POSITIVE LOGITS
     HTTP
    1.10
    HTTP
    1.07
    ://
    0.99
     HTTPS
    0.86
     headers
    0.77
     TCP
    0.77
     handshake
    0.75
     RFC
    0.74
     UDP
    0.73
     endpoint
    0.73
    Activations Density 0.018%

    No Known Activations