Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14571
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and."

    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
    +0.26
    1.3%
    1892
    +0.13
    0.6%
    1350
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1892
    +0.26
    0.06
    1265
    +0.13
    0.04
    1806
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.22
    ⓧ
    -1.07
    
    
    -0.83
    <?
    -0.81
    /***
    
    -0.77
    /**
    -0.73
    <?
    
    -0.70
    /*
    -0.68
    glMatrixMode
    -0.68
    fromnode
    -0.65
    POSITIVE LOGITS
     maneu
    1.48
     affor
    1.26
     increa
    1.25
     scrat
    1.22
     impra
    1.20
     shenan
    1.20
     inev
    1.15
     disreg
    1.14
     disagre
    1.13
     reluct
    1.12
    Activations Density 0.159%

    No Known Activations