© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 17544
    Prev
    Next
    INDEX
    Explanations

    words related to violence

    oai_token-act-pair · gpt-3.5-turbo

    references to violence or violent acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Premium
    -0.81
    Pod
    -0.77
    DK
    -0.74
    rin
    -0.72
     Boost
    -0.72
     TTL
    -0.71
     Sparkle
    -0.71
    elle
    -0.71
     Fleet
    -0.69
     Labs
    -0.69
    POSITIVE LOGITS
     violent
    3.37
    violent
    2.65
     Violent
    2.33
     violence
    2.08
     nonviolent
    2.03
    violence
    1.91
     violently
    1.79
    Viol
    1.76
     murderous
    1.71
     Violence
    1.65
    Activations Density 0.020%

    No Known Activations