Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 12-RES-JB
    6. 7779
    Prev
    Next
    INDEX
    Explanations

    references to the term "elite" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.4%
    555
    +0.13
    0.7%
    596
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.29
    0.02
    555
    +0.13
    0.01
    1872
    +0.13
    0.01
    Negative Logits
    <bos>
    -2.15
    lateinit
    -0.61
    AddWithValue
    -0.59
    HasAnnotation
    -0.58
    AutoScaleMode
    -0.56
    和田
    -0.55
    rungsseite
    -0.54
    //---
    -0.53
    /***
    
    -0.53
    glPushMatrix
    -0.53
    POSITIVE LOGITS
    Elite
    1.16
     Elite
    1.11
     elite
    1.03
     jaya
    1.02
     Breslau
    1.00
     🤣🤣
    0.96
     kyo
    0.95
     Schrö
    0.93
     élite
    0.93
     jati
    0.93
    Activations Density 0.069%

    No Known Activations