© 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. 7279
    Prev
    Next
    INDEX
    Explanations

    legal terms related to lawsuits, objections, and court proceedings

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to legal proceedings and lawsuits

    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
    die
    -0.63
     civilisation
    -0.62
     Starcraft
    -0.59
     terr
    -0.57
    isations
    -0.56
    Laughs
    -0.55
    obyl
    -0.54
     adore
    -0.53
     ze
    -0.53
    SPA
    -0.53
    POSITIVE LOGITS
     attorneys
    0.87
     subpoen
    0.87
     DOJ
    0.79
     attorney
    0.78
     filings
    0.77
     prosecutors
    0.74
     federal
    0.73
     redacted
    0.73
     plaintiffs
    0.73
     defendants
    0.73
    Activations Density 2.186%

    No Known Activations