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. 1776
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the word "kind of."

    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
    +0.33
    1.6%
    1757
    +0.11
    0.5%
    1334
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1425
    +0.33
    0.03
    1705
    +0.11
    0.03
    976
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.19
    ⓧ
    -0.72
    /***
    
    -0.69
    <tfoot>
    -0.65
    ///**
    -0.60
    glEnd
    -0.56
     /**
    
    -0.53
    glBind
    -0.53
    //{
    
    -0.53
    Marshaller
    -0.52
    POSITIVE LOGITS
     liberality
    1.03
     maroc
    1.02
     paradiso
    1.01
     impractica
    0.98
     vinci
    0.94
     cartier
    0.92
     broderie
    0.90
    lindo
    0.88
     veau
    0.88
     Abbé
    0.87
    Activations Density 0.065%

    No Known Activations