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. 1854
    Prev
    Next
    INDEX
    Explanations

    financial numerical data and social media engagement metrics

    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
    +0.39
    1.8%
    1013
    +0.14
    0.6%
    381
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.39
    0.14
    1978
    +0.14
    0.14
    1013
    +0.09
    0.12
    Negative Logits
    <bos>
    -2.40
    ⓧ
    -1.00
    
    
    -0.73
    /***
    
    -0.65
     endwhile
    -0.61
    <?
    -0.59
    <tfoot>
    -0.57
     pinulongan
    -0.57
     continue
    -0.57
    /**
    -0.56
    POSITIVE LOGITS
     applau
    0.89
     pleins
    0.89
     délib
    0.89
     fatis
    0.89
     maroc
    0.88
     nomine
    0.88
     rafra
    0.87
     Politica
    0.85
     Khart
    0.84
     marea
    0.84
    Activations Density 0.967%

    No Known Activations