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. 4-RES-JB
    6. 15117
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to legal and judicial matters

    oai_token-act-pair · gpt-3.5-turbo

    mentions of judicial or magistrate-related terms

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

    No Comments

    Negative Logits
    FORE
    -0.72
    ding
    -0.68
    never
    -0.68
    arenthood
    -0.67
    tons
    -0.66
    Brazil
    -0.64
    impl
    -0.62
    ted
    -0.62
    paren
    -0.61
    ears
    -0.60
    POSITIVE LOGITS
    istrate
    1.44
    istrates
    1.38
     magistrate
    1.23
     judge
    0.98
    merce
    0.86
     Court
    0.85
     oun
    0.85
     fined
    0.85
     actionGroup
    0.83
     court
    0.81
    Activations Density 0.016%

    No Known Activations