© 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. 10-RES-JB
    11. 2928
    Prev
    Next
    INDEX
    Explanations

    legal terms and court actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legal rulings and court decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orge
    -0.79
    riter
    -0.74
    mbuds
    -0.74
    RAW
    -0.73
    aeus
    -0.72
    nown
    -0.72
    ORGE
    -0.71
    IUM
    -0.71
    artifacts
    -0.69
     Dialogue
    -0.69
    POSITIVE LOGITS
     plaintiffs
    1.17
     unconstitutional
    1.00
     defendants
    0.95
     Plaint
    0.94
     plaintiff
    0.87
     defendant
    0.86
     Hobby
    0.85
     validity
    0.85
     constitution
    0.83
     legality
    0.83
    Activations Density 0.229%

    No Known Activations