Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 718
    Prev
    Next
    INDEX
    Explanations

    beauty-related terms and product names

    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
    +0.22
    0.8%
    876
    +0.09
    0.4%
    736
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.22
    0.07
    1366
    +0.09
    0.05
    1801
    +0.08
    0.05
    Negative Logits
    <bos>
    -2.96
    ⓧ
    -0.99
    /***
    
    -0.87
    Autoritní
    -0.80
    ///**
    -0.76
    Kontrola
    -0.72
    <?
    -0.72
    PerformLayout
    -0.70
     lutar
    -0.70
    <tfoot>
    -0.68
    POSITIVE LOGITS
     affor
    1.25
     maroc
    1.23
     malheure
    1.19
     stockholm
    1.15
     meis
    1.14
     increa
    1.13
     maneu
    1.11
     impra
    1.09
     balkon
    1.06
     lidl
    1.05
    Activations Density 0.542%

    No Known Activations