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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 8205
    Prev
    Next
    INDEX
    Explanations

    expressions related to information technology (IT) infrastructure and management, particularly focusing on network monitoring and configuration management

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.17
    1.0%
    1757
    +0.12
    0.7%
    976
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1133
    +0.17
    0.02
    1363
    +0.12
    0.02
    976
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.90
    ⓧ
    -1.17
    /***
    
    -1.07
    /**
    -0.94
    <?
    -0.87
    /*!
    
    -0.81
    
    
    -0.79
    /*
    -0.78
    #![
    -0.75
     springfox
    -0.73
    POSITIVE LOGITS
     lele
    1.19
     configuration
    1.14
     bandung
    1.12
     Configurations
    1.11
     configurations
    1.10
     Configuration
    1.07
     kasa
    1.05
     quoc
    1.03
     konfigura
    1.02
     jaya
    1.01
    Activations Density 0.067%

    No Known Activations