© 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 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. 9-RES-JB
    11. 2180
    Prev
    Next
    INDEX
    Explanations

    legal terms and courtroom-related phrases

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ultural
    -0.77
    bred
    -0.76
    obyl
    -0.75
    76561
    -0.73
    iquette
    -0.72
    Quantity
    -0.71
    oneliness
    -0.71
    perture
    -0.71
     Bulgar
    -0.69
    ankind
    -0.67
    POSITIVE LOGITS
     attorneys
    1.51
     attorney
    1.34
     suing
    1.31
     appellate
    1.29
     lawyers
    1.27
     litigation
    1.26
     filings
    1.26
     court
    1.23
     filed
    1.22
     sue
    1.22
    Activations Density 0.619%

    No Known Activations