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. 8434
    Prev
    Next
    INDEX
    Explanations

    phrases related to the value of human lives

    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
    1482
    +0.16
    0.5%
    597
    +0.13
    0.4%
    874
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1482
    +0.16
    0.03
    1296
    +0.13
    0.03
    874
    +0.13
    0.03
    Negative Logits
     elek
    -0.91
     uhr
    -0.91
     kask
    -0.88
     karton
    -0.86
     silikon
    -0.86
     kram
    -0.84
     naer
    -0.84
     makro
    -0.83
     quoc
    -0.81
     moza
    -0.81
    POSITIVE LOGITS
     lives
    1.15
    lives
    1.04
     Lives
    0.99
     LIVES
    0.96
    Lives
    0.95
     life
    0.87
    life
    0.85
     lived
    0.80
    Life
    0.78
     LIFE
    0.78
    Activations Density 0.062%

    No Known Activations