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

    Neuronpedia

    Jacobian LensNEW
    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. 4439
    Prev
    Next
    INDEX
    Explanations

    legal references and sections within legal documents

    oai_token-act-pair · gpt-3.5-turbo
    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
     orient
    -0.63
    eton
    -0.62
     ancest
    -0.62
     shaping
    -0.62
     Metatron
    -0.61
     Wander
    -0.61
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.58
    inished
    -0.56
     Mehran
    -0.56
     resisted
    -0.55
    POSITIVE LOGITS
    Section
    0.91
    (
    0.88
    bis
    0.87
    verning
    0.81
     Clause
    0.80
    702
    0.78
     clauses
    0.78
     Section
    0.77
    section
    0.77
    302
    0.75
    Activations Density 0.033%

    No Known Activations