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. 10-RES-JB
    6. 15583
    Prev
    Next
    INDEX
    Explanations

    keywords related to subscription-based services and content streaming

    oai_token-act-pair · gpt-3.5-turbo

    information related to subscription services and pricing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    afety
    -0.85
    auld
    -0.81
     Malf
    -0.79
     examiner
    -0.75
    anton
    -0.73
     conject
    -0.71
    phi
    -0.68
    Chem
    -0.68
     Ada
    -0.68
    yang
    -0.68
    POSITIVE LOGITS
     Netflix
    1.94
     Hulu
    1.87
     streaming
    1.86
    Netflix
    1.81
     Roku
    1.64
     Streaming
    1.62
    netflix
    1.51
     subscriptions
    1.50
     subscription
    1.49
     HBO
    1.43
    Activations Density 0.431%

    No Known Activations