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. 1838
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly percentages, related to polling data and election statistics

    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
    +0.25
    0.9%
    1978
    +0.10
    0.4%
    453
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1905
    +0.25
    0.04
    1223
    +0.10
    0.03
    1978
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.32
    ⓧ
    -1.03
    /**
    -0.99
    <?
    -0.83
    
    
    -0.81
     disbur
    -0.71
    /*
    -0.66
     springfox
    -0.66
     quitted
    -0.65
     endow
    -0.65
    POSITIVE LOGITS
     catég
    0.74
     marea
    0.72
     Minang
    0.71
     potest
    0.67
     justement
    0.66
     applau
    0.66
     brilla
    0.66
     Muhamma
    0.65
     monaster
    0.65
     tantum
    0.64
    Activations Density 0.088%

    No Known Activations