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. 596
    Prev
    Next
    INDEX
    Explanations

    words related to data security and privacy policies on websites

    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
    +0.20
    0.9%
    2034
    +0.16
    0.8%
    406
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.20
    0.10
    1183
    +0.16
    0.05
    2034
    +0.09
    0.08
    Negative Logits
    <bos>
    -3.41
    /***
    
    -0.68
    /*!
    
    -0.62
     broaden
    -0.62
     restore
    -0.61
     deepen
    -0.61
     build
    -0.60
     bestow
    -0.60
     rehabilitate
    -0.58
     reclaim
    -0.57
    POSITIVE LOGITS
     stockholm
    1.18
     bandung
    1.15
     panama
    1.12
     ibiza
    1.11
     nuoc
    1.10
     toledo
    1.09
     jaya
    1.08
     Minang
    1.07
     hcm
    1.07
     tucson
    1.07
    Activations Density 0.958%

    No Known Activations