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. 8-RES-JB
    6. 15806
    Prev
    Next
    INDEX
    Explanations

    mentions of judges or court-related terms

    oai_token-act-pair · gpt-3.5-turbo

    mentions of judges or judicial titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rivals
    -0.78
    haar
    -0.77
    rolet
    -0.75
    ulus
    -0.74
    ohyd
    -0.73
    zl
    -0.69
    kefeller
    -0.69
    amily
    -0.68
    irth
    -0.68
     Horde
    -0.68
    POSITIVE LOGITS
     presiding
    1.09
     overseeing
    1.00
    rooms
    0.88
     ruled
    0.87
     rulings
    0.85
     Advocate
    0.84
     Gorsuch
    0.81
    jud
    0.79
    redd
    0.79
     sentenced
    0.76
    Activations Density 0.039%

    No Known Activations