© 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. 2582
    Prev
    Next
    INDEX
    Explanations

    phrases related to interruptions or disruptions

    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.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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    32
    +0.09
    0.3%
    509
    +0.07
    0.2%
    196
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    459
    +0.09
    0.03
    1718
    +0.07
    0.02
    2033
    +0.06
    0.02
    Negative Logits
    <bos>
    -1.17
    
    -0.89
    /**
    -0.85
    /***
    -0.80
    <?
    -0.75
    ⓧ
    -0.74
    /*
    -0.73
    <?
    -0.65
    /*!
    -0.63
    новниш
    -0.60
    POSITIVE LOGITS
     interruption
    1.99
     interrupted
    1.96
     interruptions
    1.95
     interrupting
    1.71
     disruption
    1.70
     interrupt
    1.70
     disruptions
    1.62
     interrupts
    1.59
     disrupted
    1.55
     interference
    1.45
    Activations Density 0.165%

    No Known Activations