© 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. 2698
    Prev
    Next
    INDEX
    Explanations

    words related to spices and cooking ingredients

    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
    597
    +0.11
    0.4%
    325
    +0.09
    0.3%
    795
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.11
    0.03
    890
    +0.09
    0.03
    597
    +0.09
    0.03
    Negative Logits
     &___
    -0.61
    IContainer
    -0.59
    WriteLiteral
    -0.58
    WireFormatLite
    -0.57
    RectangleBorder
    -0.55
    ുറ
    -0.55
    準
    -0.54
     reached
    -0.54
    poll
    -0.54
    MessageOf
    -0.53
    POSITIVE LOGITS
     spice
    2.73
     Spice
    2.40
    spice
    2.22
    Spice
    2.21
     spices
    2.12
     Spices
    1.93
     spiced
    1.71
     increa
    1.63
     impra
    1.62
     maneu
    1.62
    Activations Density 0.212%

    No Known Activations