© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 372
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and its varying usages in phrases

    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
    1.9%
    1334
    +0.11
    0.5%
    1763
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1415
    +0.39
    0.04
    1334
    +0.11
    0.03
    1095
    +0.09
    0.02
    Negative Logits
    <bos>
    -1.69
     intersper
    -0.98
    /**
    -0.88
    <?
    -0.82
    
    -0.78
    ⓧ
    -0.75
    /***
    -0.71
     endow
    -0.68
     /**
    -0.66
     faw
    -0.59
    POSITIVE LOGITS
    Să
    0.60
    bánh
    0.54
    indest
    0.52
    ?}",
    0.52
    \!\
    0.50
    muñ
    0.49
    Wpf
    0.49
     indicato
    0.49
    Dermott
    0.48
    lindo
    0.48
    Activations Density 0.089%

    No Known Activations