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. 6248
    Prev
    Next
    INDEX
    Explanations

    information related to Olympic Games and sports events

    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
    0.9%
    32
    +0.11
    0.6%
    1065
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1065
    +0.17
    0.03
    479
    +0.11
    0.02
    1049
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.72
    ⓧ
    -0.97
    /**
    -0.94
    <?
    -0.81
    /*
    -0.80
    HasAnnotation
    -0.79
    
    
    -0.76
    #
    -0.69
    /***
    
    -0.66
     defray
    -0.65
    POSITIVE LOGITS
     Banjar
    1.35
     Minang
    1.20
     Karang
    1.18
     olympic
    1.13
     Palembang
    1.11
     Jambi
    1.11
     Bekasi
    1.09
     Olympic
    1.08
     Meksi
    1.05
     Juf
    1.05
    Activations Density 0.103%

    No Known Activations