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. 9196
    Prev
    Next
    INDEX
    Explanations

    news articles about criminal activities, law enforcement, and legal proceedings

    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
    +0.21
    0.7%
    1213
    +0.07
    0.2%
    908
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1213
    +0.21
    0.07
    216
    +0.07
    0.05
    648
    +0.07
    0.05
    Negative Logits
    <bos>
    -1.67
    ⓧ
    -1.00
    /**
    -0.88
    
    
    -0.82
    /*
    -0.81
    <?
    -0.80
    /***
    
    -0.78
    JAKARTA
    -0.72
    <?
    
    -0.71
    //};
    -0.59
    POSITIVE LOGITS
     Spani
    0.74
     Meksi
    0.72
     Gnaden
    0.69
     riva
    0.68
     Departement
    0.66
     seksi
    0.65
     Muhamma
    0.64
     Ferdin
    0.63
     Thron
    0.63
     soulign
    0.62
    Activations Density 0.291%

    No Known Activations