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. 15088
    Prev
    Next
    INDEX
    Explanations

    medical terms or descriptions related to long-term patient care and treatment outcomes

    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
    +0.24
    1.2%
    1896
    +0.11
    0.6%
    1870
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1597
    +0.24
    0.03
    1904
    +0.11
    0.03
    1081
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.80
    <?
    
    -0.67
    ///**
    -0.66
     introduce
    -0.63
     inject
    -0.63
     waive
    -0.62
     propagate
    -0.61
     assemble
    -0.60
     partake
    -0.60
     disseminate
    -0.60
    POSITIVE LOGITS
     sovere
    1.30
     Minang
    1.29
     perfon
    1.29
     quoique
    1.26
     unwarran
    1.23
     Khart
    1.22
     magis
    1.22
     nomine
    1.21
     embodi
    1.20
     prado
    1.16
    Activations Density 0.179%

    No Known Activations