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. 6162
    Prev
    Next
    INDEX
    Explanations

    terms related to sports plays and actions

    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
    0.6%
    1842
    +0.09
    0.3%
    1905
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1905
    +0.17
    0.04
    1290
    +0.09
    0.03
    736
    +0.07
    0.03
    Negative Logits
    <bos>
    -2.11
    /***
    
    -0.64
    /**
    -0.59
     peintures
    -0.57
     prêtres
    -0.56
    
    
    -0.56
    public
    -0.54
    <?
    
    -0.54
     defray
    -0.53
    /*
    -0.52
    POSITIVE LOGITS
     Minang
    1.07
     véhic
    0.98
     silikon
    0.89
     applau
    0.88
     Banjar
    0.86
     Guanajuato
    0.86
     electrica
    0.84
     Portugu
    0.84
     Minangkabau
    0.84
     karton
    0.83
    Activations Density 0.095%

    No Known Activations