© 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. 20736
    Prev
    Next
    INDEX
    Explanations

    legal terms related to court judgments

    oai_token-act-pair · gpt-3.5-turbo

    legal terms related to court decisions and rulings

    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
    ohyd
    -0.78
    ongh
    -0.73
    udeau
    -0.72
     Growth
    -0.72
     airst
    -0.71
     goose
    -0.65
     lifelong
    -0.63
    otor
    -0.63
    pload
    -0.63
    atomic
    -0.63
    POSITIVE LOGITS
    making
    0.83
    sup
    0.81
     rulings
    0.80
     upholding
    0.79
    Sup
    0.78
    uary
    0.76
    Reviewed
    0.74
     Scalia
    0.72
    maker
    0.72
     Cosponsors
    0.71
    Activations Density 0.066%

    No Known Activations