© 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. 14132
    Prev
    Next
    INDEX
    Explanations

    descriptions of violent incidents involving physical altercations

    oai_token-act-pair · gpt-3.5-turbo

    events related to violent crimes and 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
     Tolkien
    -0.87
     Inher
    -0.77
     splend
    -0.77
     honoured
    -0.74
     fortnight
    -0.73
     optim
    -0.72
     immortality
    -0.70
     UNESCO
    -0.70
     Nobel
    -0.69
     bestselling
    -0.69
    POSITIVE LOGITS
    police
    0.95
    Officers
    0.92
     paramedics
    0.91
    Police
    0.88
     police
    0.87
     grabbed
    0.86
     altercation
    0.84
     handcuffed
    0.83
     yelling
    0.83
     ensued
    0.83
    Activations Density 0.907%

    No Known Activations