© 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 · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10832
    Prev
    Next
    INDEX
    Explanations

    references to military-related terms and activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.20
    0.8%
    1778
    +0.14
    0.5%
    405
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.20
    0.05
    405
    +0.14
    0.04
    168
    +0.13
    0.04
    Negative Logits
     erad
    -0.98
     accla
    -0.92
     reconno
    -0.87
     fortn
    -0.86
     volunte
    -0.85
     scrat
    -0.84
     intermitt
    -0.83
     attemp
    -0.82
     maneu
    -0.82
     disgra
    -0.82
    POSITIVE LOGITS
     military
    1.19
    military
    1.13
    Military
    1.09
     Military
    1.06
     militares
    0.90
     MILITARY
    0.84
     militar
    0.71
    ilitary
    0.71
    ITARY
    0.70
     army
    0.67
    Activations Density 0.075%

    No Known Activations