© 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. 4-RES-JB
    11. 13045
    Prev
    Next
    INDEX
    Explanations

    keywords related to military operations and deployments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to military or security personnel being positioned or assigned to locations

    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
    nings
    -0.69
    Honest
    -0.67
    fall
    -0.65
    bm
    -0.65
    cause
    -0.63
    she
    -0.63
    Buzz
    -0.62
    lic
    -0.62
    osity
    -0.62
    lihood
    -0.61
    POSITIVE LOGITS
     stationed
    1.16
    ilitary
    1.09
     patrolling
    0.89
     barracks
    0.87
     troops
    0.85
    anamo
    0.83
     aboard
    0.81
    rons
    0.81
     patrols
    0.80
     Marines
    0.79
    Activations Density 0.046%

    No Known Activations