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. 10020
    Prev
    Next
    INDEX
    Explanations

    references related to financial transactions and legal actions

    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%
    1763
    +0.10
    0.6%
    1520
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1059
    +0.18
    0.03
    1837
    +0.10
    0.03
    878
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.12
    
    
    -0.72
    ⓧ
    -0.69
    /***
    
    -0.68
    JspWriter
    -0.61
    Высота
    -0.60
    public
    -0.59
     become
    -0.58
     distribute
    -0.56
    //---
    -0.56
    POSITIVE LOGITS
     maneu
    1.41
     increa
    1.41
     Minang
    1.39
     inconce
    1.39
     Charg
    1.39
     maroc
    1.38
     ricardo
    1.38
     rodriguez
    1.37
     uncin
    1.37
     bandung
    1.37
    Activations Density 0.096%

    No Known Activations