© 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 EvalsExportsAPI 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. 19313
    Prev
    Next
    INDEX
    Explanations

    instances of violent actions such as shootings, attacks, stabbings, and bombings

    oai_token-act-pair · gpt-3.5-turbo

    instances of violence or attacks

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ennial
    -0.84
     aster
    -0.78
    ripp
    -0.73
    cancer
    -0.69
    ãĤ´ãĥ³
    -0.69
     ç¥ŀ
    -0.68
    onyms
    -0.66
    alog
    -0.65
    ANN
    -0.64
    eric
    -0.64
    POSITIVE LOGITS
     unarmed
    0.91
     parked
    0.91
     bystanders
    0.86
     fleeing
    0.85
     bystand
    0.82
     attempting
    0.79
     parach
    0.79
     bicy
    0.79
     sleeping
    0.73
     suspected
    0.72
    Activations Density 0.434%

    No Known Activations