© 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. 3-RES-JB
    11. 16791
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and judicial matters, particularly focusing on the Supreme Court and judicial appointments

    oai_token-act-pair · gpt-3.5-turbo

    references to the judicial system and its related components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Laf
    -0.92
     Motorsport
    -0.74
    retched
    -0.72
     Belg
    -0.72
    ettel
    -0.71
    mble
    -0.69
    iple
    -0.69
     Ong
    -0.69
     Lanc
    -0.68
     Constant
    -0.68
    POSITIVE LOGITS
     Gorsuch
    0.95
    Reviewed
    0.89
    eyed
    0.82
    ocrats
    0.81
    ervatives
    0.79
    endment
    0.79
    Democrats
    0.78
    Republicans
    0.77
     Scalia
    0.73
     justices
    0.71
    Activations Density 0.077%

    No Known Activations