© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5131
    Prev
    Next
    INDEX
    Explanations

    descriptions related to legal rulings

    oai_token-act-pair · gpt-3.5-turbo

    legal terms and phrases related to court rulings and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworld
    -0.86
    ople
    -0.76
    ohyd
    -0.73
    anners
    -0.72
    icides
    -0.70
    icide
    -0.69
    dden
    -0.67
    phen
    -0.67
    atha
    -0.66
    pload
    -0.66
    POSITIVE LOGITS
     legalizing
    0.85
     upholding
    0.84
    making
    0.79
     overturn
    0.79
    Sup
    0.79
     rulings
    0.77
     Judicial
    0.76
    maker
    0.75
    Judge
    0.70
     invalid
    0.70
    Activations Density 0.058%

    No Known Activations