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. 6240
    Prev
    Next
    INDEX
    Explanations

    texts related to fundraising events, charity walks, and community support activities

    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
    0.9%
    1778
    +0.07
    0.3%
    2011
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1603
    +0.25
    0.05
    697
    +0.07
    0.05
    798
    +0.07
    0.05
    Negative Logits
    <bos>
    -2.82
    ⓧ
    -1.01
    
    
    -0.87
    <?
    -0.75
    /***
    
    -0.74
    afterEach
    -0.74
    <?
    
    -0.69
    //---
    -0.67
    /**
    -0.63
    /*++
    -0.62
    POSITIVE LOGITS
     Minang
    1.58
     lele
    1.53
     bandung
    1.52
     Jambi
    1.50
     hcm
    1.48
     Juf
    1.46
     Palembang
    1.38
     Karang
    1.38
     reluct
    1.37
     Banjar
    1.33
    Activations Density 0.454%

    No Known Activations