© 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. 2780
    Prev
    Next
    INDEX
    Explanations

    proper names related to a specific person named "Victoria"

    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
    1187
    +0.07
    0.3%
    11
    +0.07
    0.3%
    1276
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1187
    +0.07
    0.02
    144
    +0.07
    0.02
    337
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.86
    
    -0.66
    <?
    -0.64
    BUYER
    -0.63
     tű
    -0.62
    break
    -0.62
    /*
    -0.62
    ///**
    -0.61
    GroupLayout
    -0.61
    //
    -0.61
    POSITIVE LOGITS
     Victoria
    2.45
     VICTORIA
    2.34
    Victoria
    2.27
     impra
    1.97
     increa
    1.95
     disagre
    1.89
     reluct
    1.85
     accla
    1.84
     victoria
    1.81
     maneu
    1.80
    Activations Density 0.119%

    No Known Activations