© 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. 2805
    Prev
    Next
    INDEX
    Explanations

    the word "Glass" appearing in the text

    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
    50
    +0.17
    1.1%
    896
    +0.14
    0.9%
    1222
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    896
    +0.17
    0.04
    899
    +0.14
    0.04
    1385
    +0.11
    0.03
    Negative Logits
    <bos>
    -3.06
    ⓧ
    -0.74
    EndProject
    -0.73
    <tfoot>
    -0.69
    /***
    -0.68
    PerformLayout
    -0.68
    ExtendWith
    -0.67
    Ngoài
    -0.65
     GeoNames
    -0.64
    ///**
    -0.62
    POSITIVE LOGITS
     Juf
    1.33
     Minang
    1.26
     glass
    1.23
    Glass
    1.23
     Glass
    1.21
     maroc
    1.15
     véhic
    1.15
     Jambi
    1.14
     maneu
    1.14
     saar
    1.12
    Activations Density 0.126%

    No Known Activations