© 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. 4-RES-JB
    11. 2122
    Prev
    Next
    INDEX
    Explanations

    Legal terms related to breaches of various kinds

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "breach" and related legal violations

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

    No Comments

    Negative Logits
    uana
    -0.80
     livest
    -0.73
    minist
    -0.71
     Towns
    -0.67
     corrid
    -0.66
    ohyd
    -0.65
     redistributed
    -0.64
     taxp
    -0.63
    endar
    -0.63
     unification
    -0.61
    POSITIVE LOGITS
     breaches
    1.00
     breach
    0.94
    aucus
    0.85
     Breach
    0.83
    terness
    0.81
     breached
    0.78
     breaching
    0.71
    hole
    0.71
    breakers
    0.67
    mson
    0.66
    Activations Density 0.010%

    No Known Activations