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. 8081
    Prev
    Next
    INDEX
    Explanations

    discussion or involvement in law, politics, human rights, and domestic violence

    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
    +0.16
    0.6%
    490
    +0.10
    0.4%
    1505
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.16
    0.05
    902
    +0.10
    0.04
    462
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.82
    /***
    
    -0.73
    Geplaatst
    -0.66
    ⓧ
    -0.64
    ///**
    -0.60
    /*!
    
    -0.60
    contentLoaded
    -0.58
    <?
    
    -0.58
    <_>
    -0.52
    estimable
    -0.52
    POSITIVE LOGITS
     considér
    1.04
     vété
    0.86
     configureStore
    0.84
     curé
    0.83
     resultList
    0.83
     useRouter
    0.82
     Docteur
    0.80
     voluto
    0.78
     écout
    0.78
     fameux
    0.78
    Activations Density 0.362%

    No Known Activations