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. 10-RES-JB
    6. 1829
    Prev
    Next
    INDEX
    Explanations

    adverbs that describe the degree or quality of various actions or states

    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.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    0.9%
    468
    +0.12
    0.5%
    872
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1446
    +0.24
    0.05
    478
    +0.12
    0.06
    1763
    +0.09
    0.06
    Negative Logits
    <bos>
    -2.89
    
    
    -0.95
    ⓧ
    -0.92
    <?
    -0.78
    /**
    -0.78
    })();
    
    -0.75
    //{
    
    -0.74
     don
    -0.72
     decide
    -0.70
     pull
    -0.69
    POSITIVE LOGITS
     lidl
    1.80
     michelin
    1.76
     cabrio
    1.71
     lamborghini
    1.70
     bordeaux
    1.69
     sappi
    1.67
     embodi
    1.64
     applau
    1.63
     stockholm
    1.60
     chrysler
    1.58
    Activations Density 0.638%

    No Known Activations