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

    Neuronpedia

    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. 4-RES-JB
    11. 14366
    Prev
    Next
    INDEX
    Explanations

    words related to violent incidents like shootings and killings, especially involving law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    terms related to violence and fatal incidents involving firearms and police interactions

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

    No Comments

    Negative Logits
    ebus
    -0.79
    amina
    -0.67
    Bey
    -0.64
    coat
    -0.62
     Canal
    -0.61
    arity
    -0.61
    ULE
    -0.60
    VIEW
    -0.60
    stream
    -0.59
    inion
    -0.59
    POSITIVE LOGITS
    uggest
    1.09
    mith
    1.06
    hips
    1.05
    ettings
    1.03
    poons
    1.02
    paces
    1.02
    hip
    0.93
    chool
    0.86
    hooting
    0.86
    afety
    0.86
    Activations Density 0.073%

    No Known Activations