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. 8261
    Prev
    Next
    INDEX
    Explanations

    health-related terms related to stomach issues

    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
    667
    +0.13
    0.5%
    50
    +0.13
    0.5%
    1678
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1493
    +0.13
    0.03
    5
    +0.13
    0.03
    864
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.19
    ⓧ
    -0.85
    /**
    -0.81
     AssemblyCompany
    -0.77
    
    
    -0.71
    <?
    -0.68
     embo
    -0.61
    <tfoot>
    -0.59
    HasForeignKey
    -0.58
     Freien
    -0.57
    POSITIVE LOGITS
     pank
    1.06
     cæ
    1.05
     lemp
    0.99
     Manufact
    0.98
     seksi
    0.98
     maroc
    0.97
     stomach
    0.96
     saar
    0.96
     fua
    0.94
     keramik
    0.93
    Activations Density 0.214%

    No Known Activations