© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5025
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal beliefs and strong opinions

    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
    +0.28
    1.1%
    845
    +0.07
    0.3%
    998
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.28
    -0.01
    628
    +0.07
    0.06
    1473
    +0.07
    0.06
    Negative Logits
    <bos>
    -3.17
    ///**
    -0.81
    Autoritní
    -0.80
    /***
    -0.76
    EndGlobalSection
    -0.76
    /**
    -0.73
    /*
    -0.66
    
    -0.65
    новништво
    -0.64
    InjectAttribute
    -0.61
    POSITIVE LOGITS
     cartier
    0.75
    atguigu
    0.70
     fameux
    0.70
     pymysql
    0.69
     carrefour
    0.67
     Talvez
    0.65
     quoique
    0.64
     contextLoads
    0.64
    stdarg
    0.63
     Şi
    0.63
    Activations Density 1.206%

    No Known Activations