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. 2-RES-JB
    6. 16990
    Prev
    Next
    INDEX
    Explanations

    legal and judiciary-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the judicial system and related processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lund
    -0.74
    ÃŁ
    -0.73
     Horus
    -0.73
    VP
    -0.73
    jc
    -0.72
    ramid
    -0.72
     Banner
    -0.71
    lished
    -0.69
    uld
    -0.69
    arter
    -0.68
    POSITIVE LOGITS
     judicial
    1.00
     justice
    0.94
     oversight
    0.92
     rulings
    0.91
    iciary
    0.90
     appellate
    0.87
    justice
    0.87
     scrutiny
    0.87
    icial
    0.83
     inquiry
    0.82
    Activations Density 0.006%

    No Known Activations