© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 2058
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ann" and variations related to it

    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
    1323
    +0.14
    0.8%
    1691
    +0.13
    0.8%
    50
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.14
    0.02
    1323
    +0.13
    0.02
    240
    +0.12
    0.02
    Negative Logits
    <bos>
    -1.93
     so
    -0.66
    ValueGenerated
    -0.62
    SizeMode
    -0.61
    Referències
    -0.61
      
    -0.60
    so
    -0.59
    商品説明
    -0.58
    <em>
    -0.58
    脚注の使い方
    -0.57
    POSITIVE LOGITS
     shenan
    1.53
     reluct
    1.42
     Ann
    1.41
     indestru
    1.29
    Ann
    1.27
     Anne
    1.27
     maneu
    1.27
     quoique
    1.25
     emphat
    1.25
     accla
    1.24
    Activations Density 0.054%

    No Known Activations