© 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. 11-RES-JB
    11. 21647
    Prev
    Next
    INDEX
    Explanations

    legal terms and legal procedures

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and phrases related to court proceedings and petitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cub
    -0.85
    natureconservancy
    -0.77
    BILITIES
    -0.77
     Walt
    -0.75
     Stronghold
    -0.75
     Columb
    -0.74
    lando
    -0.73
    lymp
    -0.72
    Florida
    -0.70
    ebus
    -0.68
    POSITIVE LOGITS
     bench
    1.13
     CBI
    1.12
     Bench
    1.08
     adjourn
    1.08
     magistrate
    1.07
     Lok
    1.05
     Bombay
    1.05
     FIR
    1.01
    Justice
    1.01
     colleg
    1.00
    Activations Density 0.306%

    No Known Activations