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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5658
    Prev
    Next
    INDEX
    Explanations

    text related to religious beliefs and doctrines, specifically related to Christianity

    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
    +0.19
    0.7%
    1842
    +0.10
    0.4%
    394
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2037
    +0.19
    0.06
    509
    +0.10
    0.04
    872
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.63
    ⓧ
    -0.84
    /**
    -0.83
    /***
    
    -0.78
    ///**
    -0.69
    <?
    
    -0.68
     springfox
    -0.68
    
    
    -0.68
    webElementXpaths
    -0.67
     implement
    -0.66
    POSITIVE LOGITS
     bandung
    1.41
     wien
    1.38
     thut
    1.33
     stockholm
    1.29
     lara
    1.29
     lyon
    1.27
     aen
    1.26
     napoli
    1.26
     Juf
    1.24
     fta
    1.24
    Activations Density 0.221%

    No Known Activations