© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 18709
    Prev
    Next
    INDEX
    Explanations

    patterns related to legal proceedings and court decisions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal judgments or court rulings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ispers
    -0.69
    anish
    -0.69
    PsyNetMessage
    -0.68
    lash
    -0.65
     whispers
    -0.65
    rients
    -0.65
    cffffcc
    -0.64
    nces
    -0.62
     briefings
    -0.61
     announcements
    -0.61
    POSITIVE LOGITS
     unconstitutional
    1.32
     violated
    1.29
     unlawfully
    1.28
     improperly
    1.22
     violates
    1.13
     ineligible
    1.13
     violate
    1.12
     negligent
    1.12
     breached
    1.11
     infring
    1.09
    Activations Density 0.354%

    No Known Activations