© 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. 2918
    Prev
    Next
    INDEX
    Explanations

    references to modes of transportation involving passengers

    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
    166
    +0.08
    0.3%
    544
    +0.08
    0.3%
    31
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.08
    0.03
    1426
    +0.08
    0.03
    2030
    +0.07
    0.02
    Negative Logits
    <bos>
    -1.61
    /*
    -0.82
    /**
    -0.81
    
    -0.72
    ⓧ
    -0.71
    lateinit
    -0.68
    /***
    -0.68
    interface
    -0.66
    define
    -0.65
    ૌ
    -0.65
    POSITIVE LOGITS
     passenger
    2.26
     Passenger
    2.15
     Passengers
    2.05
    Passenger
    1.94
    passenger
    1.88
     passengers
    1.80
     stockholm
    1.71
     Juf
    1.70
    Passengers
    1.69
     aen
    1.63
    Activations Density 0.113%

    No Known Activations