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. 763
    Prev
    Next
    INDEX
    Explanations

    words related to yield, such as "yielded", "yield", and "yielding"

    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
    468
    +0.12
    0.4%
    876
    +0.09
    0.3%
    938
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    849
    +0.12
    0.04
    468
    +0.09
    0.03
    316
    +0.08
    0.03
    Negative Logits
    aqui
    -0.42
    AppRoutingModule
    -0.42
     manualmente
    -0.41
    fromnode
    -0.41
    },{
    
    -0.41
    šanās
    -0.40
     Adicion
    -0.40
    Voci
    -0.39
     Atual
    -0.39
    andaag
    -0.39
    POSITIVE LOGITS
     Yields
    0.94
     tupperware
    0.86
     ecru
    0.86
     hairc
    0.84
     abnorm
    0.83
     kram
    0.80
     naer
    0.79
     swarovski
    0.79
     yield
    0.79
     vogli
    0.77
    Activations Density 0.310%

    No Known Activations