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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 17487
    Prev
    Next
    INDEX
    Explanations

    terms related to the legal concept of "due process."

    oai_token-act-pair · gpt-3.5-turbo

    references to legal processes and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nas
    -0.74
    bring
    -0.74
    Stars
    -0.72
    has
    -0.71
    iosyn
    -0.71
    Tes
    -0.69
    uku
    -0.69
    hap
    -0.68
    Drop
    -0.67
    mund
    -0.67
    POSITIVE LOGITS
     clauses
    0.97
     clause
    0.95
     protections
    0.94
     syndrome
    0.92
     doctrine
    0.89
     exemptions
    0.82
     designation
    0.82
     fallacy
    0.81
     violation
    0.80
     principles
    0.78
    Activations Density 0.259%

    No Known Activations