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. 6145
    Prev
    Next
    INDEX
    Explanations

    instances of conditional statements, specifically those starting with "if"

    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
    +0.25
    1.6%
    1265
    +0.13
    0.8%
    404
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.25
    0.09
    1265
    +0.13
    0.07
    757
    +0.12
    0.07
    Negative Logits
    <bos>
    -3.36
    ⓧ
    -1.01
    <?
    -0.91
    
    
    -0.78
    Vegeu
    -0.73
    Enllaços
    -0.69
    /**
    -0.67
    ///**
    -0.62
    <?
    
    -0.61
    HasAnnotation
    -0.61
    POSITIVE LOGITS
     stockholm
    1.22
     accla
    1.17
     wien
    1.16
     Confe
    1.15
     maneu
    1.15
     eiffel
    1.14
     inev
    1.14
     jacques
    1.14
     Manufact
    1.13
     disgra
    1.11
    Activations Density 0.233%

    No Known Activations