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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 47
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to the concept of 'ever'

    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
    +0.18
    1.1%
    251
    +0.12
    0.7%
    1671
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    251
    +0.18
    0.04
    1865
    +0.12
    0.04
    1363
    +0.12
    0.04
    Negative Logits
    <bos>
    -3.12
    ///**
    -0.77
    /***
    
    -0.76
    <>
    
    -0.63
    Vegeu
    -0.63
    
    
    -0.62
    public
    -0.62
    <?
    
    -0.62
    <?
    -0.61
    lateinit
    -0.61
    POSITIVE LOGITS
     chrysler
    1.62
     hilux
    1.38
     stockholm
    1.38
     affor
    1.36
     pollut
    1.35
     maneu
    1.34
     cabrio
    1.33
     lidl
    1.32
     déchir
    1.32
     fortn
    1.30
    Activations Density 0.051%

    No Known Activations