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. 2894
    Prev
    Next
    INDEX
    Explanations

    words related to strength and growth

    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
    1036
    +0.09
    0.3%
    1416
    +0.09
    0.3%
    143
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1265
    +0.09
    0.04
    1416
    +0.09
    0.03
    1036
    +0.09
    0.01
    Negative Logits
     ananas
    -0.80
     myn
    -0.80
     Keny
    -0.79
     Juf
    -0.78
     kokos
    -0.76
     ricardo
    -0.71
     karna
    -0.70
     sergio
    -0.70
     zara
    -0.70
     Augu
    -0.69
    POSITIVE LOGITS
     faster
    1.14
     easier
    1.09
     better
    1.08
     stronger
    1.08
     healthier
    1.08
     safer
    1.07
     harder
    1.05
     quicker
    1.04
     happier
    1.03
     clearer
    1.01
    Activations Density 0.193%

    No Known Activations