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. 675
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical activities and achievements

    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
    1.5%
    478
    +0.16
    1.1%
    1967
    +0.14
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.22
    0.16
    1967
    +0.16
    0.12
    1108
    +0.14
    0.13
    Negative Logits
    <bos>
    -4.54
    ⓧ
    -1.34
    <?
    -1.22
    
    
    -1.17
    /***
    
    -1.12
    /**
    -1.09
    /*!
    
    -0.97
     intersper
    -0.93
     disbur
    -0.88
     springfox
    -0.87
    POSITIVE LOGITS
     corrom
    0.86
     seksi
    0.86
     tristes
    0.78
     marea
    0.76
     maroc
    0.76
     saar
    0.75
     ceramica
    0.74
     vasi
    0.74
     uhr
    0.74
     kafe
    0.74
    Activations Density 1.335%

    No Known Activations