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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - Dec 2023
    3. GPT2-Small
    4. MLP Post
    5. 6-MLP-OAI
    6. 24307
    Prev
    Next
    INDEX
    Explanations

    the phrase "as always"

    oai_token-act-pair · gpt-4-turbo

    "always" in "As always", plus the comma after, and the words/phrases "we", "we will", "you", "please", "you can", "any", "given", or "a" if rightafter

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    No Known Activations