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. 14023
    Prev
    Next
    INDEX
    Explanations

    words related to deployment, especially in a military context

    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
    1778
    +0.15
    0.6%
    1870
    +0.14
    0.5%
    990
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.15
    0.03
    990
    +0.14
    0.02
    240
    +0.12
    0.02
    Negative Logits
     qualifi
    -0.57
     haver
    -0.51
     Fag
    -0.51
    Fag
    -0.51
    Xna
    -0.50
     Schna
    -0.50
     Brag
    -0.50
     FSC
    -0.48
    Sic
    -0.46
     Paredes
    -0.46
    POSITIVE LOGITS
     deployment
    1.29
     deployments
    1.25
     deploy
    1.25
     deployed
    1.18
     Deployment
    1.16
     deploying
    1.12
    deployment
    1.08
    deployed
    1.07
     Deploy
    1.04
    deploy
    1.03
    Activations Density 0.063%

    No Known Activations