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. 795
    Prev
    Next
    INDEX
    Explanations

    contact and location information, potentially on websites

    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
    +0.16
    0.6%
    1343
    +0.07
    0.3%
    1804
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.16
    0.03
    1390
    +0.07
    0.03
    1419
    +0.06
    0.03
    Negative Logits
    <bos>
    -1.10
    /**
    -1.00
    ⓧ
    -0.96
    <?
    
    -0.91
    /***
    
    -0.90
    <?
    -0.89
     quitted
    -0.89
    
    
    -0.81
    ///**
    -0.77
    /*
    -0.77
    POSITIVE LOGITS
     montagna
    0.61
     تضيفلها
    0.59
     pioggia
    0.57
     Karang
    0.55
     spiaggia
    0.55
     expédi
    0.54
     Sardegna
    0.53
     Banjar
    0.53
    dropna
    0.52
     déliv
    0.51
    Activations Density 0.069%

    No Known Activations