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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14052
    Prev
    Next
    INDEX
    Explanations

    mentions of military deployments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to military deployment and troop movements

    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
     Topic
    -0.88
    terms
    -0.82
    iquid
    -0.81
    agate
    -0.81
    bid
    -0.74
     clipping
    -0.74
    inventoryQuantity
    -0.74
    weet
    -0.73
    Parent
    -0.72
    conom
    -0.71
    POSITIVE LOGITS
     troops
    1.93
     soldiers
    1.75
     marines
    1.65
     infantry
    1.65
     army
    1.62
     cavalry
    1.59
     Marines
    1.57
     armies
    1.54
     militia
    1.53
     armed
    1.52
    Activations Density 0.559%

    No Known Activations