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. 662
    Prev
    Next
    INDEX
    Explanations

    terms related to policies and guidelines for combating counterfeit medicines and providing support for those impacted by strokes

    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
    +0.27
    1.1%
    198
    +0.13
    0.5%
    227
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.27
    0.12
    1252
    +0.13
    0.10
    1682
    +0.09
    0.08
    Negative Logits
    <bos>
    -2.81
    ⓧ
    -0.87
    
    
    -0.85
    <?
    -0.75
    /**
    -0.74
     put
    -0.71
    <?
    
    -0.68
    }{||
    -0.67
     send
    -0.67
     expand
    -0.66
    POSITIVE LOGITS
     Juf
    1.75
     lele
    1.68
     Khart
    1.64
     wien
    1.60
     aen
    1.58
     mef
    1.57
     Minang
    1.57
     Keny
    1.56
     fta
    1.56
     saar
    1.55
    Activations Density 1.820%

    No Known Activations