Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 1892
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal proceedings and court documents

    oai_token-act-pair · gpt-3.5-turbo

    references to various courts and legal jurisdictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocument
    -0.66
    eele
    -0.66
    ec
    -0.66
     ful
    -0.64
    icidal
    -0.62
    pak
    -0.61
    esc
    -0.61
    aning
    -0.60
    ku
    -0.60
     Saban
    -0.59
    POSITIVE LOGITS
     judge
    1.09
     Judge
    1.09
    rooms
    0.99
     Circuit
    0.93
     magistrate
    0.87
     Clerk
    0.86
     clerk
    0.85
    Judge
    0.83
     sided
    0.81
    istrate
    0.81
    Activations Density 0.050%

    No Known Activations