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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 5635
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "define" or phrases related to defining and describing

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.19
    1.0%
    1296
    +0.10
    0.5%
    596
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1036
    +0.19
    0.01
    596
    +0.10
    0.02
    1141
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.82
    /***
    
    -0.86
    Referencie
    -0.80
    
    
    -0.74
    /*!
    
    -0.69
    <?
    -0.68
    ⓧ
    -0.67
    Zdroje
    -0.63
     rehabilitate
    -0.63
     leaped
    -0.63
    POSITIVE LOGITS
     definition
    1.06
     lele
    1.04
     nomine
    1.04
     definitions
    1.02
    definition
    0.99
     Minang
    0.98
     Definition
    0.98
     vasi
    0.96
     saar
    0.96
     silikon
    0.95
    Activations Density 0.088%

    No Known Activations