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. 5502
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions or evaluations

    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
    +0.29
    1.3%
    161
    +0.08
    0.3%
    1950
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    62
    +0.29
    0.06
    161
    +0.08
    0.05
    1784
    +0.07
    0.06
    Negative Logits
    <bos>
    -3.62
    /***
    
    -0.82
    <?
    -0.81
    ⓧ
    -0.70
    ///**
    -0.69
    /**
    -0.61
    //*/
    -0.61
    Kontrola
    -0.59
    <?
    
    -0.57
    //---
    -0.57
    POSITIVE LOGITS
     bandung
    1.17
     lele
    1.11
     uhr
    1.04
     Minang
    0.99
     jawa
    0.99
     ananas
    0.98
     kase
    0.95
     maroc
    0.94
     seksi
    0.93
     saar
    0.93
    Activations Density 0.857%

    No Known Activations