© 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. 10-RES-JB
    11. 1236
    Prev
    Next
    INDEX
    Explanations

    The neuron is looking for mentions of various attacks, conflicts, and military operations involving different countries and groups

    oai_token-act-pair · gpt-3.5-turbo

    references to violent actions and attacks against entities, particularly in a geopolitical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obin
    -0.73
    ozo
    -0.69
    indal
    -0.68
    olkien
    -0.64
    ibal
    -0.63
    cribed
    -0.62
    igmat
    -0.62
     Shift
    -0.62
    rang
    -0.60
     Redemption
    -0.60
    POSITIVE LOGITS
     targets
    1.01
     convoy
    0.90
     unarmed
    0.83
     bystanders
    0.80
     pedestrians
    0.80
     buildings
    0.78
     premises
    0.78
     civilians
    0.77
     innoc
    0.77
     offices
    0.76
    Activations Density 0.392%

    No Known Activations