© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2713
    Prev
    Next
    INDEX
    Explanations

    phrases related to presentations or public speaking events

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    1870
    +0.08
    0.3%
    50
    +0.07
    0.3%
    783
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1003
    +0.08
    0.03
    1867
    +0.07
    0.03
    579
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.45
    
    -0.76
    <?
    -0.71
    /***
    -0.69
    <?
    -0.65
    ⓧ
    -0.63
    /*
    -0.62
    /**
    -0.62
     invade
    -0.60
    /*!
    -0.58
    POSITIVE LOGITS
     presentation
    2.12
     Presentation
    1.97
     presentations
    1.95
     Presentations
    1.72
    presentation
    1.71
    Presentation
    1.70
    Presentations
    1.54
     lele
    1.51
     PRESENTATION
    1.51
     Minang
    1.47
    Activations Density 0.135%

    No Known Activations