Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-RES-JB
    6. 19579
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the term "Justice Department."

    oai_token-act-pair · gpt-3.5-turbo

    the word "Justice" and its associations within a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÃŁ
    -0.75
    laus
    -0.67
    vae
    -0.67
    estate
    -0.63
    vre
    -0.62
    amping
    -0.61
    bsite
    -0.61
     bra
    -0.61
     bombard
    -0.60
     geographically
    -0.60
    POSITIVE LOGITS
    Justice
    1.31
     Justice
    1.25
    justice
    1.21
     justice
    0.91
     JUSTICE
    0.90
     GOODMAN
    0.80
    iciary
    0.79
    suits
    0.78
     Advocate
    0.75
     Assistance
    0.74
    Activations Density 0.013%

    No Known Activations