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. 12-RES-JB
    6. 7878
    Prev
    Next
    INDEX
    Explanations

    punctuations and sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.39
    1.8%
    2034
    +0.18
    0.8%
    1535
    +0.16
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1535
    +0.39
    0.16
    1959
    +0.18
    0.18
    2034
    +0.16
    0.18
    Negative Logits
    <bos>
    -2.26
    FTFY
    -0.92
    Lmfao
    -0.88
    /***
    
    -0.86
    ⓧ
    -0.85
    <?
    -0.81
    ///**
    -0.81
    Ikr
    -0.80
    /**
    -0.79
     springfox
    -0.75
    POSITIVE LOGITS
     vété
    1.18
     désol
    1.13
     épu
    1.08
     véhic
    1.08
     paradiso
    1.06
     héro
    1.06
     aveug
    1.05
     soulign
    1.05
     pleins
    1.05
     écout
    1.04
    Activations Density 1.105%

    No Known Activations