© 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. 774
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court orders and legal actions, particularly focusing on injunctions

    oai_token-act-pair · gpt-3.5-turbo

    legal terms related to injunctions and restraining orders

    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
    rics
    -0.83
     Growth
    -0.80
     UX
    -0.73
    olls
    -0.71
    ols
    -0.68
     Univers
    -0.68
    hematic
    -0.67
    onut
    -0.66
    apest
    -0.64
    uld
    -0.63
    POSITIVE LOGITS
     injunction
    1.21
     restraining
    1.08
     decree
    0.93
     subpoen
    0.91
    ishment
    0.88
     proceedings
    0.85
     adjud
    0.83
     prohibiting
    0.83
     forb
    0.82
     warr
    0.81
    Activations Density 0.010%

    No Known Activations