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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15307
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and recipes for specific dishes

    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
    +0.30
    1.2%
    1013
    +0.11
    0.4%
    876
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1284
    +0.30
    0.07
    736
    +0.11
    0.07
    1013
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.02
    /***
    
    -0.94
    ⓧ
    -0.93
    /**
    -0.87
     Mlle
    -0.86
    <?
    
    -0.85
    <?
    -0.83
    ///**
    -0.82
    
    
    -0.78
     crê
    -0.75
    POSITIVE LOGITS
    󠁢
    0.62
     gră
    0.61
     aproximativ
    0.58
     prieten
    0.56
     copii
    0.55
     oameni
    0.55
     mici
    0.54
     resistentes
    0.53
     schim
    0.53
     ameste
    0.53
    Activations Density 0.360%

    No Known Activations