© 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. 9-RES-JB
    11. 10248
    Prev
    Next
    INDEX
    Explanations

    actions of physical violence

    oai_token-act-pair · gpt-3.5-turbo

    actions related to physical violence and aggression

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    stellar
    -0.77
    oux
    -0.71
    natureconservancy
    -0.70
    enment
    -0.70
     redes
    -0.65
     havens
    -0.65
    MSN
    -0.64
    ETF
    -0.63
    True
    -0.63
    Reloaded
    -0.62
    POSITIVE LOGITS
     him
    0.90
     bystanders
    0.84
     unconscious
    0.77
     someone
    0.75
     injure
    0.71
    aband
    0.69
     violently
    0.69
    lasses
    0.68
     rocks
    0.68
     repeatedly
    0.68
    Activations Density 0.174%

    No Known Activations