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. 3-RES-JB
    6. 8549
    Prev
    Next
    INDEX
    Explanations

    words related to legal and judiciary matters

    oai_token-act-pair · gpt-3.5-turbo

    references to the judicial system and its processes

    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
     Banner
    -0.82
    lished
    -0.77
     Horus
    -0.76
    lund
    -0.74
    alos
    -0.74
    ramid
    -0.73
     Bulg
    -0.73
    eem
    -0.72
    eworld
    -0.72
    jc
    -0.71
    POSITIVE LOGITS
     rulings
    1.03
     justice
    0.93
     judicial
    0.92
     oversight
    0.92
     activism
    0.85
     exceptions
    0.85
    justice
    0.85
     scrutiny
    0.84
     misconduct
    0.82
     hearings
    0.82
    Activations Density 0.005%

    No Known Activations