© 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. 8-RES-JB
    11. 14144
    Prev
    Next
    INDEX
    Explanations

    actions involving physical violence, such as hitting, stabbing, or shooting

    oai_token-act-pair · gpt-3.5-turbo

    actions involving physical violence or assaults

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    lio
    -0.80
    ilight
    -0.71
     Reconstruction
    -0.67
    chart
    -0.65
    imilation
    -0.65
    Angelo
    -0.64
    Shin
    -0.64
    iary
    -0.64
    Reilly
    -0.62
    bright
    -0.62
    POSITIVE LOGITS
     impunity
    1.54
     fists
    1.13
     ease
    1.10
     scissors
    1.07
    stood
    1.04
    standing
    1.00
     gust
    0.99
     dignity
    0.95
     knives
    0.94
     utmost
    0.93
    Activations Density 0.133%

    No Known Activations