© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12872
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "proper" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to standards and protocols for proper conduct and safety

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     wildly
    -0.73
     Pione
    -0.72
    herer
    -0.68
    ---------
    -0.67
    find
    -0.66
     sadly
    -0.65
     Melvin
    -0.65
     unexpectedly
    -0.65
    cli
    -0.62
    true
    -0.62
    POSITIVE LOGITS
    tarian
    1.25
     precautions
    1.02
     sized
    1.01
     attire
    0.95
     functioning
    0.92
     etiquette
    0.91
     disposal
    0.90
     noun
    0.89
    tarians
    0.89
     safeguards
    0.88
    Activations Density 0.060%

    No Known Activations