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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 1259
    Prev
    Next
    INDEX
    Explanations

    text related to patents and patent applications

    oai_token-act-pair · gpt-3.5-turbo

    terms related to patents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olis
    -0.80
    eous
    -0.69
    Esc
    -0.68
    anooga
    -0.68
    adelphia
    -0.67
    é»Ĵ
    -0.67
    deen
    -0.67
    leans
    -0.66
    risis
    -0.66
     Crisis
    -0.65
    POSITIVE LOGITS
     patent
    3.76
     patents
    3.61
     Patent
    3.10
     patented
    2.39
     trademark
    1.76
     copyright
    1.57
     antitrust
    1.55
     trademarks
    1.55
     inventions
    1.45
     invention
    1.43
    Activations Density 0.009%

    No Known Activations