© 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. 10-RES-JB
    11. 4776
    Prev
    Next
    INDEX
    Explanations

    terms related to apologies and expressions of regret

    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
    +0.24
    1.2%
    538
    +0.10
    0.5%
    1742
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    538
    +0.24
    0.02
    1742
    +0.10
    0.02
    1363
    +0.09
    0.02
    Negative Logits
    <bos>
    -2.97
    ⓧ
    -1.01
    
    -0.87
    <?
    -0.81
    /**
    -0.74
    ///**
    -0.74
    /***
    -0.70
    HasAnnotation
    -0.69
    //};
    -0.67
    HasIndex
    -0.63
    POSITIVE LOGITS
     apology
    1.11
     Czechos
    1.10
     maneu
    1.04
     apologizing
    1.02
     Minang
    1.00
     liverpool
    0.91
     bandung
    0.90
     apologe
    0.90
     apologies
    0.90
     Batam
    0.88
    Activations Density 0.037%

    No Known Activations