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

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 12738
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal issues and litigation

    oai_token-act-pair · gpt-3.5-turbo

    references to legal actions and litigation processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erd
    -0.96
    eele
    -0.94
    olls
    -0.84
    rolet
    -0.83
    ordinate
    -0.81
    atomic
    -0.81
    ODE
    -0.79
    bern
    -0.74
    olen
    -0.73
    ebus
    -0.71
    POSITIVE LOGITS
     proceedings
    0.87
     litigation
    0.85
    suits
    0.84
    emate
    0.77
     settlement
    0.73
     subpoen
    0.73
    suit
    0.72
     challeng
    0.71
     disputes
    0.71
     filings
    0.71
    Activations Density 0.013%

    No Known Activations