© 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. 12-RES-JB
    11. 4093
    Prev
    Next
    INDEX
    Explanations

    nouns related to legal entities and processes, including court-related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the Supreme Court and its related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    ptoms
    -0.74
    ku
    -0.72
    OPLE
    -0.69
    icro
    -0.68
     Typh
    -0.67
    tun
    -0.64
    atars
    -0.62
    daq
    -0.61
    BILITIES
    -0.61
    cult
    -0.60
    POSITIVE LOGITS
     justices
    1.32
     nominee
    0.99
     ruling
    0.95
     rulings
    0.94
     vacancy
    0.93
     upheld
    0.89
     rul
    0.87
     decision
    0.87
     Justice
    0.84
     justice
    0.84
    Activations Density 0.049%

    No Known Activations