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. 6741
    Prev
    Next
    INDEX
    Explanations

    various forms of quotation marks or apostrophes

    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
    1034
    +0.21
    1.1%
    50
    +0.20
    1.0%
    1101
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1034
    +0.21
    0.04
    1404
    +0.20
    0.04
    545
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.48
    ⓧ
    -1.30
    <?
    -1.24
    
    
    -1.23
    /**
    -1.21
     дописавши
    -1.11
    /*
    -0.88
    <?
    
    -0.80
    /***
    
    -0.69
    💼
    -0.68
    POSITIVE LOGITS
     valencia
    1.04
     Cuer
    0.92
    dison
    0.91
     santiago
    0.85
     Compañ
    0.84
     seksi
    0.83
     Peque
    0.82
     unlaw
    0.82
     ‘
    0.82
     giovanni
    0.79
    Activations Density 0.047%

    No Known Activations