© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 2488
    Prev
    Next
    INDEX
    Explanations

    language related to patents and patent-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to patents and patent-related concepts

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

    No Comments

    Negative Logits
     Isles
    -0.76
     Revel
    -0.74
    de
    -0.68
    ombies
    -0.68
    hani
    -0.66
    Thom
    -0.66
     Helpful
    -0.66
    real
    -0.64
    ilib
    -0.64
     Helm
    -0.64
    POSITIVE LOGITS
     infringement
    1.01
     patent
    0.97
     patents
    0.97
    enced
    0.93
     portfolio
    0.82
     examiner
    0.80
     Patent
    0.77
    ulent
    0.76
    onomy
    0.75
     licensing
    0.75
    Activations Density 0.015%

    No Known Activations