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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 7476
    Prev
    Next
    INDEX
    Explanations

    references to the word "monster" followed by various other terms, possibly related to the context of toys, magical creatures, or inner struggles

    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
    1520
    +0.16
    0.8%
    1937
    +0.15
    0.8%
    1339
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1520
    +0.16
    0.03
    1256
    +0.15
    0.03
    966
    +0.14
    0.02
    Negative Logits
    <bos>
    -2.28
    /**
    -0.89
    <?
    -0.77
    Autoritní
    -0.74
    ⓧ
    -0.73
    
    -0.73
    /*
    -0.67
    /***
    -0.67
    Více
    -0.66
     defaultstate
    -0.62
    POSITIVE LOGITS
     maksi
    1.87
     saar
    1.75
     kasa
    1.68
     hina
    1.66
     jaya
    1.59
     Minang
    1.56
     lele
    1.53
     naer
    1.50
     territo
    1.49
     seksi
    1.48
    Activations Density 0.286%

    No Known Activations