© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2514
    Prev
    Next
    INDEX
    Explanations

    phrases related to fortunate or lucky situations

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.11
    0.4%
    1876
    +0.05
    0.2%
    560
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.11
    0.03
    1876
    +0.05
    0.02
    1651
    +0.04
    0.02
    Negative Logits
    <bos>
    -1.21
    ⓧ
    -0.97
    ///**
    -0.85
    /***
    -0.80
    <?
    -0.74
    <!--
    -0.71
    })();
    -0.69
    //<
    -0.68
    
    -0.66
    /*++
    -0.66
    POSITIVE LOGITS
     Fortunately
    1.99
     Luckily
    1.93
     maneu
    1.90
     Thankfully
    1.89
     fortunately
    1.88
     luckily
    1.82
    Fortunately
    1.82
    Luckily
    1.79
     affor
    1.71
    Thankfully
    1.69
    Activations Density 0.063%

    No Known Activations