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. 728
    Prev
    Next
    INDEX
    Explanations

    situations involving legal disputes and personal conflict

    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
    +0.31
    1.1%
    1843
    +0.12
    0.4%
    946
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.31
    0.13
    1843
    +0.12
    0.06
    1097
    +0.11
    0.07
    Negative Logits
    <bos>
    -3.34
    <?
    -0.68
    InvalidProtocol
    -0.65
    
    
    -0.65
     chè
    -0.64
    /*!
    
    -0.63
     Ceinture
    -0.62
    ftagPool
    -0.60
     /**
    
    -0.60
     springfox
    -0.59
    POSITIVE LOGITS
     accla
    1.35
     maneu
    1.35
     resear
    1.32
     reluct
    1.29
     Juf
    1.20
     impra
    1.19
     unspeak
    1.16
     disgra
    1.16
     shenan
    1.16
     unve
    1.15
    Activations Density 0.736%

    No Known Activations