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. 15128
    Prev
    Next
    INDEX
    Explanations

    terms related to sports match updates or game play-by-play descriptions

    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
    0.8%
    994
    +0.11
    0.5%
    1978
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.18
    0.17
    1870
    +0.11
    0.04
    1978
    +0.08
    0.14
    Negative Logits
    <bos>
    -3.48
    ⓧ
    -0.81
    /**
    -0.81
    /***
    
    -0.79
    <!--[
    -0.74
    
    
    -0.74
    //---
    -0.72
    //{
    
    -0.71
    IVEREF
    -0.68
    Autoritní
    -0.67
    POSITIVE LOGITS
     ecru
    1.46
     swarovski
    1.36
     lamborghini
    1.33
     eiffel
    1.32
     chrysler
    1.27
     pymysql
    1.21
     lidl
    1.21
     madonna
    1.19
     murano
    1.19
     toledo
    1.18
    Activations Density 4.516%

    No Known Activations