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. 0-RES-JB
    6. 14384
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning legal professionals or their actions

    oai_token-act-pair · gpt-3.5-turbo

    references to judges and judicial roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cum
    -0.66
    hi
    -0.63
     âĸĪ
    -0.63
     sqor
    -0.62
    -(
    -0.61
    gewater
    -0.60
    load
    -0.60
    van
    -0.59
    Cap
    -0.59
    mop
    -0.58
    POSITIVE LOGITS
     judges
    3.89
     Judges
    2.93
     judge
    2.39
     justices
    2.03
    Judge
    1.99
     Judge
    1.98
     jurors
    1.94
     courts
    1.82
     judiciary
    1.71
     Courts
    1.66
    Activations Density 0.017%

    No Known Activations