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. 10-RES-JB
    6. 6839
    Prev
    Next
    INDEX
    Explanations

    associations between dietary factors and health outcomes

    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.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.30
    1.1%
    736
    +0.10
    0.4%
    283
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.30
    0.06
    1380
    +0.10
    0.02
    1870
    +0.09
    0.03
    Negative Logits
    <bos>
    -2.25
    PerformLayout
    -0.84
     PicClick
    -0.75
    Geplaatst
    -0.74
    BeginInit
    -0.70
    ždý
    -0.70
     initComponents
    -0.69
    .
    -0.67
    HideFlags
    -0.67
    oredCriteria
    -0.67
    POSITIVE LOGITS
     disagre
    2.40
     increa
    2.17
     maneu
    2.11
     emphat
    2.09
     milf
    2.06
     guarante
    2.04
     fuf
    2.02
     ftu
    2.02
     unwarran
    2.00
     desir
    1.98
    Activations Density 0.624%

    No Known Activations