© 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. 2866
    Prev
    Next
    INDEX
    Explanations

    the word "choice" in various contexts

    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
    50
    +0.10
    0.4%
    528
    +0.07
    0.3%
    596
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    416
    +0.10
    0.04
    992
    +0.07
    0.04
    208
    +0.05
    0.04
    Negative Logits
    <bos>
    -1.75
    public
    -0.70
    ///**
    -0.66
    /***
    -0.65
     put
    -0.65
     continue
    -0.63
    //
    -0.62
    Kontrola
    -0.60
    //
    -0.60
     have
    -0.60
    POSITIVE LOGITS
     choice
    2.00
     Choice
    1.92
     CHOICE
    1.81
    choice
    1.80
    Choice
    1.75
     stockholm
    1.67
     aen
    1.65
     meis
    1.59
     choices
    1.58
     maroc
    1.58
    Activations Density 0.090%

    No Known Activations