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. 19164
    Prev
    Next
    INDEX
    Explanations

    mentions of patents and trademarks, particularly in the context of legal challenges and disputes

    oai_token-act-pair · gpt-3.5-turbo

    references to patent and trademark processes or related legal terms

    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
     Homeless
    -0.87
     brunch
    -0.87
     sober
    -0.85
     Salvation
    -0.80
     mayoral
    -0.80
     Cabin
    -0.78
     Budget
    -0.76
    adelphia
    -0.75
     dining
    -0.75
    usterity
    -0.74
    POSITIVE LOGITS
     patents
    2.18
     patent
    2.06
     Patent
    1.85
     trademarks
    1.58
     patented
    1.56
     trademark
    1.53
     copyright
    1.52
    yrights
    1.50
     infringement
    1.44
     infring
    1.44
    Activations Density 0.271%

    No Known Activations