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. 6-RES-JB
    6. 14765
    Prev
    Next
    INDEX
    Explanations

    terms related to retirement and post-career activities

    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
    +0.18
    1.0%
    1034
    +0.10
    0.5%
    1921
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1921
    +0.18
    0.02
    1437
    +0.10
    0.02
    1306
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.90
    ⓧ
    -0.88
    <?
    -0.72
    /***
    
    -0.66
    /**
    -0.63
     disbur
    -0.62
    <?
    
    -0.60
     distribute
    -0.59
    /*++
    -0.57
     assure
    -0.56
    POSITIVE LOGITS
    Retirement
    1.12
     Retirement
    1.09
     retirement
    1.08
     Retired
    0.98
    retirement
    0.94
    Retired
    0.94
     jaya
    0.91
     Jambi
    0.90
     retiring
    0.89
     Retire
    0.89
    Activations Density 0.087%

    No Known Activations