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. 5403
    Prev
    Next
    INDEX
    Explanations

    companies or products known for specific features or characteristics

    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
    +0.28
    1.1%
    1839
    +0.08
    0.3%
    1691
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    843
    +0.28
    0.05
    605
    +0.08
    0.02
    683
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.40
    <?
    -0.81
    /**
    -0.78
    
    
    -0.76
    /***
    
    -0.74
    ⓧ
    -0.71
     mustered
    -0.69
    /*
    -0.69
     peered
    -0.68
    /*!
    
    -0.63
    POSITIVE LOGITS
    arture
    0.95
     applau
    0.86
     Somal
    0.85
     kyo
    0.83
    uxx
    0.83
     jaya
    0.82
     Minang
    0.82
     haup
    0.82
     bandung
    0.82
     sembl
    0.82
    Activations Density 0.561%

    No Known Activations