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. 1154
    Prev
    Next
    INDEX
    Explanations

    quantitative data related to viewer statistics and fundraising efforts

    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%
    690
    +0.10
    0.4%
    1445
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1033
    +0.24
    0.06
    563
    +0.10
    0.04
    690
    +0.10
    0.04
    Negative Logits
    <bos>
    -3.39
    Autoritní
    -0.65
    };*/
    -0.62
    /***
    
    -0.61
    /*!
    
    -0.55
    //---
    -0.55
    public
    -0.54
    //--
    -0.53
    },{
    
    -0.53
    //});
    -0.53
    POSITIVE LOGITS
     soulign
    1.01
     pollut
    1.00
     shayari
    0.97
     véhic
    0.90
     Minang
    0.90
     scattata
    0.88
     🤣🤣
    0.87
    capulco
    0.86
     Jambi
    0.86
     friable
    0.86
    Activations Density 0.577%

    No Known Activations