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. 8-RES-JB
    6. 15332
    Prev
    Next
    INDEX
    Explanations

    email-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    general elements and calls to action in content, particularly involving subscriptions and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imperson
    -0.79
     reversing
    -0.72
     acting
    -0.72
     mas
    -0.70
     eternity
    -0.69
     itself
    -0.68
     fleeing
    -0.68
     yet
    -0.68
     directing
    -0.66
     therefore
    -0.66
    POSITIVE LOGITS
    Subscribe
    1.06
    Privacy
    1.03
    Spons
    0.96
    Learn
    0.95
    Disclaimer
    0.93
    Comments
    0.93
    FAQ
    0.91
    License
    0.91
    Share
    0.89
    Posted
    0.89
    Activations Density 0.301%

    No Known Activations