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. 20966
    Prev
    Next
    INDEX
    Explanations

    websites or online platforms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "site."

    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
    mares
    -0.74
    Īè
    -0.73
    drawn
    -0.72
    ween
    -0.69
    ropy
    -0.67
    eating
    -0.66
    Increases
    -0.66
    liam
    -0.65
    laughs
    -0.63
     ILCS
    -0.63
    POSITIVE LOGITS
     site
    3.65
     sites
    2.67
     Site
    2.55
    site
    2.52
    Site
    2.34
     website
    2.16
     Sites
    2.13
    sites
    1.89
     webpage
    1.59
    bsite
    1.57
    Activations Density 0.018%

    No Known Activations