© 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. 11-RES-JB
    11. 20754
    Prev
    Next
    INDEX
    Explanations

    specific legal terms used in lawsuits and court cases

    oai_token-act-pair · gpt-3.5-turbo

    references to court cases and legal proceedings

    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
    isine
    -0.70
    ritical
    -0.69
    TABLE
    -0.68
    RN
    -0.65
    ontent
    -0.63
    pter
    -0.63
     flashes
    -0.63
    edia
    -0.63
    ffen
    -0.62
    ãĥ¼ãĥĨ
    -0.62
    POSITIVE LOGITS
     cases
    1.73
     case
    1.72
     litigation
    1.60
     lawsuit
    1.57
     lawsuits
    1.56
     Cases
    1.39
     Case
    1.36
    Case
    1.34
     prosecutions
    1.29
     defamation
    1.28
    Activations Density 0.398%

    No Known Activations