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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 188
    Prev
    Next
    INDEX
    Explanations

    mentions of strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.34
    1.7%
    1870
    +0.15
    0.8%
    555
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.34
    0.03
    251
    +0.15
    0.02
    1806
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.06
    /***
    
    -0.80
    //---
    -0.62
    ///**
    -0.62
     /**
    
    -0.60
    //*/
    -0.60
    
    
    -0.59
    <?
    
    -0.59
    ⓧ
    -0.54
    /****
    -0.54
    POSITIVE LOGITS
     strategy
    1.28
     strategia
    1.21
     Strategy
    1.17
    strategy
    1.15
     STRATEGY
    1.13
     strategies
    1.12
    Strategy
    1.05
     Strategies
    1.04
    strategies
    1.03
    égias
    1.02
    Activations Density 0.030%

    No Known Activations