© 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. 13647
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court proceedings and judges

    oai_token-act-pair · gpt-3.5-turbo

    references to courts and judges within the legal context

    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
    zsche
    -0.76
    byn
    -0.74
    ãĥ¡
    -0.70
     manifold
    -0.66
     hol
    -0.65
     plent
    -0.65
     mun
    -0.64
    sung
    -0.62
    bull
    -0.62
     sake
    -0.62
    POSITIVE LOGITS
    Judge
    0.89
     Judge
    0.88
    orneys
    0.84
    rontal
    0.83
     judge
    0.82
    Attorney
    0.79
     jurisdiction
    0.78
    istrate
    0.77
     Detention
    0.75
    Executive
    0.75
    Activations Density 0.041%

    No Known Activations