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. 5517
    Prev
    Next
    INDEX
    Explanations

    instances related to legal actions or challenges

    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
    +0.18
    0.9%
    453
    +0.18
    0.8%
    1499
    +0.17
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.18
    0.24
    453
    +0.18
    0.23
    1216
    +0.17
    0.14
    Negative Logits
    <bos>
    -3.47
    
    
    -1.18
    <?
    -1.18
    ⓧ
    -1.07
     intersper
    -0.99
    /***
    
    -0.95
    /**
    -0.95
    <?
    
    -0.90
     /**
    
    -0.85
    //...
    -0.80
    POSITIVE LOGITS
     saar
    1.18
     Minang
    1.15
     Muhamma
    1.08
     soulign
    1.04
     nece
    1.03
     aen
    1.02
     Coim
    1.02
     hina
    1.01
     Ueb
    0.99
     Jambi
    0.98
    Activations Density 5.672%

    No Known Activations