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. 940
    Prev
    Next
    INDEX
    Explanations

    instances of the word "loose" and its variations, often in contexts implying a lack of strictness or clarity

    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
    680
    +0.19
    1.0%
    50
    +0.17
    0.9%
    1272
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    680
    +0.19
    0.02
    1272
    +0.17
    0.02
    1942
    +0.14
    0.01
    Negative Logits
    <bos>
    -2.65
    </thead>
    -0.81
    VIAF
    -0.77
    param
    -0.72
    return
    -0.71
    public
    -0.71
    quad
    -0.70
    HasIndex
    -0.70
    			
    -0.70
    /**
    
    -0.69
    POSITIVE LOGITS
     maneu
    1.87
     madonna
    1.87
     Juf
    1.84
     jorge
    1.83
     disagre
    1.80
     accla
    1.80
     stockholm
    1.77
     excru
    1.77
     roberto
    1.73
     ftu
    1.72
    Activations Density 0.049%

    No Known Activations