© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 4821
    Prev
    Next
    INDEX
    Explanations

    terms related to humanitarian issues and crises

    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
    +0.20
    1.0%
    1870
    +0.17
    0.9%
    1068
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.20
    0.01
    1363
    +0.17
    0.02
    1233
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.75
    ⓧ
    -0.96
    
    -0.82
    /**
    -0.73
     defray
    -0.72
    /***
    -0.71
     disbur
    -0.69
    <?
    -0.69
    fromnode
    -0.68
     rejoin
    -0.66
    POSITIVE LOGITS
     humanitarian
    0.97
     riva
    0.93
     ados
    0.88
     marea
    0.87
     Humanitarian
    0.87
     croce
    0.87
    lijah
    0.85
     indispensables
    0.85
     plastico
    0.85
     paradiso
    0.84
    Activations Density 0.066%

    No Known Activations