Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8367
    Prev
    Next
    INDEX
    Explanations

    details related to military actions and casualties in conflict zones

    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
    184
    +0.15
    0.5%
    1842
    +0.13
    0.4%
    394
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.15
    0.05
    792
    +0.13
    0.03
    184
    +0.11
    0.02
    Negative Logits
     vola
    -0.74
     ananas
    -0.73
     maroc
    -0.73
     tille
    -0.72
     merav
    -0.71
     marte
    -0.70
     drap
    -0.70
     Kontrol
    -0.70
     stik
    -0.68
     élev
    -0.68
    POSITIVE LOGITS
     felicity
    0.74
     liberality
    0.73
     Glou
    0.67
     Middles
    0.65
     McLaugh
    0.64
     unlaw
    0.62
     Leyden
    0.60
     shewn
    0.60
    /**
    0.60
     pamph
    0.59
    Activations Density 0.305%

    No Known Activations