© 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. 12-RES-JB
    11. 2394
    Prev
    Next
    INDEX
    Explanations

    instances of words related to sexual misconduct

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    terms related to sexual misconduct and abuse

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    IVERS
    -0.86
     Closed
    -0.74
    atl
    -0.67
    bley
    -0.64
    CB
    -0.64
    nas
    -0.63
    çĽ
    -0.63
    ign
    -0.62
    hillary
    -0.62
    LB
    -0.62
    POSITIVE LOGITS
     assault
    1.01
     battery
    1.01
     advances
    0.99
     misconduct
    0.95
     assaults
    0.94
     touching
    0.93
     mol
    0.93
     exploitation
    0.92
     gratification
    0.90
     abuse
    0.90
    Activations Density 0.054%

    No Known Activations