© 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. 1-RES-JB
    11. 3347
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and court proceedings specifically involving judges

    oai_token-act-pair · gpt-3.5-turbo

    mentions of judges in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.79
    uld
    -0.78
    kefeller
    -0.76
    haar
    -0.73
    td
    -0.70
    ulated
    -0.69
    ulate
    -0.68
    ijk
    -0.68
    reek
    -0.68
    irst
    -0.67
    POSITIVE LOGITS
     Advocate
    0.94
     judge
    0.90
    ģĸ
    0.86
     lashes
    0.79
    Judge
    0.79
     reviewer
    0.79
    maker
    0.79
     rulings
    0.77
     judges
    0.77
    ĪĴ
    0.76
    Activations Density 0.014%

    No Known Activations