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. 1881
    Prev
    Next
    INDEX
    Explanations

    the term "characteristics" and related descriptors

    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
    +0.20
    1.0%
    1839
    +0.13
    0.6%
    687
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1839
    +0.20
    0.03
    68
    +0.13
    0.02
    1125
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.31
    /***
    
    -0.92
    ///**
    -0.62
    Referencie
    -0.61
    /*!
    
    -0.59
    <tfoot>
    -0.57
     assistir
    -0.57
    Odkazy
    -0.55
    
    
    -0.54
    </>
    
    -0.54
    POSITIVE LOGITS
     fatis
    1.26
     lele
    1.25
     meis
    1.24
     thut
    1.24
     wien
    1.22
     vne
    1.21
     kasa
    1.19
     saar
    1.19
     effe
    1.18
     saha
    1.18
    Activations Density 0.090%

    No Known Activations