Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 800
    Prev
    Next
    INDEX
    Explanations

    phrases centered around the concept of discussing or talking about various topics

    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
    +0.34
    1.7%
    938
    +0.11
    0.5%
    866
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    938
    +0.34
    0.05
    1573
    +0.11
    0.04
    866
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.67
    <?
    -0.74
    /**
    -0.71
    /***
    
    -0.68
    ⓧ
    -0.68
    ///**
    -0.66
    
    
    -0.61
    font
    -0.59
    /*++
    -0.57
    <?
    
    -0.57
    POSITIVE LOGITS
     bandung
    1.43
     sovere
    1.36
     Minang
    1.35
     lidl
    1.32
     Juf
    1.32
     autunno
    1.31
     eiffel
    1.30
     affor
    1.28
     Czechos
    1.27
     milano
    1.27
    Activations Density 0.161%

    No Known Activations