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. 7771
    Prev
    Next
    INDEX
    Explanations

    phrases related to balancing goals and resources

    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
    +0.25
    0.9%
    2034
    +0.16
    0.6%
    1013
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.25
    0.10
    1013
    +0.16
    0.13
    2034
    +0.12
    0.12
    Negative Logits
    <bos>
    -2.41
    //*/
    -0.97
    /***
    
    -0.80
    ඉ
    -0.71
    Kontrola
    -0.71
    ඒ
    -0.69
    ඔ
    -0.69
    Vaata
    -0.67
    posób
    -0.67
    උ
    -0.66
    POSITIVE LOGITS
     lele
    1.00
     optik
    0.90
     bandung
    0.90
     kaos
    0.88
     benzina
    0.85
     Glou
    0.85
    heyd
    0.85
     seoul
    0.84
     NDEBUG
    0.84
     actionTypes
    0.84
    Activations Density 1.227%

    No Known Activations