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. 2408
    Prev
    Next
    INDEX
    Explanations

    references to legal cases, court decisions, and court proceedings

    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
    0.7%
    817
    +0.08
    0.3%
    872
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1901
    +0.18
    0.04
    2025
    +0.08
    0.04
    914
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.95
    ⓧ
    -0.94
    
    
    -0.70
    <?
    -0.65
    /**
    -0.65
    <?
    
    -0.60
    /*
    -0.60
     arrange
    -0.57
     localize
    -0.55
     refrigerate
    -0.55
    POSITIVE LOGITS
     Minang
    1.03
     Karang
    0.98
     maroc
    0.97
     Jambi
    0.93
     Pekan
    0.93
     Præ
    0.92
     Muhamma
    0.92
     kasa
    0.91
     Juf
    0.91
     Nguy
    0.90
    Activations Density 0.305%

    No Known Activations