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. 14761
    Prev
    Next
    INDEX
    Explanations

    content related to consumer products, such as mower types, books on crochet, and descriptions of different Pokemon types

    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
    +0.27
    1.8%
    478
    +0.15
    1.0%
    812
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    920
    +0.27
    0.09
    658
    +0.15
    0.08
    1806
    +0.13
    0.07
    Negative Logits
    <bos>
    -3.54
    <?
    -0.72
    HasIndex
    -0.71
    lateinit
    -0.69
    ⓧ
    -0.67
    /***
    
    -0.66
    ///**
    -0.65
    औ
    -0.65
    /*
    -0.64
    #
    -0.62
    POSITIVE LOGITS
     Minang
    1.68
     unlaw
    1.61
     disagre
    1.60
     sovere
    1.55
     increa
    1.54
     unwarran
    1.53
     accla
    1.53
     inev
    1.52
     squa
    1.50
     impractica
    1.50
    Activations Density 0.181%

    No Known Activations