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. 14812
    Prev
    Next
    INDEX
    Explanations

    sentences related to love and compassion from religious texts and articles

    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
    +0.27
    1.3%
    227
    +0.10
    0.5%
    394
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.27
    0.11
    1784
    +0.10
    0.15
    1095
    +0.10
    0.10
    Negative Logits
    <bos>
    -3.01
    /**
    -0.99
    ⓧ
    -0.99
    /*
    -0.93
    <?
    -0.91
    
    
    -0.85
    })();
    
    -0.69
    ///**
    -0.66
     eventually
    -0.65
    #
    -0.65
    POSITIVE LOGITS
     maneu
    1.66
     accla
    1.63
     reluct
    1.48
     affor
    1.48
     Khart
    1.47
     increa
    1.46
     Juf
    1.44
     impra
    1.43
     Keny
    1.43
     Hez
    1.42
    Activations Density 7.005%

    No Known Activations