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. 6118
    Prev
    Next
    INDEX
    Explanations

    mentions of drafts in a specific context

    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
    +0.18
    1.1%
    680
    +0.12
    0.7%
    1961
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1101
    +0.18
    0.02
    1562
    +0.12
    0.02
    1059
    +0.12
    0.02
    Negative Logits
    <bos>
    -3.13
    CodeDom
    -0.74
    /***
    
    -0.72
    /*!
    
    -0.71
    ⓧ
    -0.71
    IonicModule
    -0.70
    ///**
    -0.66
    CreateIndex
    -0.65
    mbggenerated
    -0.65
    addComponent
    -0.65
    POSITIVE LOGITS
     affor
    1.67
     maroc
    1.56
     maneu
    1.49
     stockholm
    1.49
     impra
    1.48
     increa
    1.45
     Minang
    1.41
     Juf
    1.38
     disagre
    1.38
     emphat
    1.38
    Activations Density 0.073%

    No Known Activations