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. 891
    Prev
    Next
    INDEX
    Explanations

    terms related to structural attributes and characteristics of various systems or designs

    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
    +0.26
    1.0%
    1870
    +0.12
    0.5%
    1150
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.26
    0.08
    1269
    +0.12
    0.06
    1206
    +0.09
    0.07
    Negative Logits
    <bos>
    -2.88
    /***
    
    -0.69
    /*++
    -0.67
    displayquote
    -0.66
    HasIndex
    -0.65
    HasForeignKey
    -0.61
    /*!
    
    -0.60
    <tfoot>
    -0.60
    //{
    
    -0.57
    Odkazy
    -0.57
    POSITIVE LOGITS
     impra
    1.53
     milf
    1.53
     affor
    1.53
     maneu
    1.51
     increa
    1.49
     disreg
    1.44
     hentai
    1.43
     snoopy
    1.41
     jurassic
    1.40
     madonna
    1.39
    Activations Density 0.952%

    No Known Activations