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. 818
    Prev
    Next
    INDEX
    Explanations

    phrases related to tracking and monitoring

    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
    +0.23
    1.5%
    687
    +0.16
    1.0%
    479
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.23
    0.03
    1464
    +0.16
    0.03
    479
    +0.13
    0.03
    Negative Logits
    <bos>
    -2.81
    else
    -0.73
    ൊ
    -0.71
     AssemblyCompany
    -0.68
    //
    -0.67
     հղումներ
    -0.65
    ComponentModel
    -0.64
    ⁡
    -0.63
    <thead>
    -0.63
    util
    -0.62
    POSITIVE LOGITS
     increa
    2.07
     accla
    2.04
     affor
    2.01
     maneu
    1.93
     impra
    1.92
     strick
    1.87
     reluct
    1.87
     disagre
    1.84
     unspeak
    1.84
     inev
    1.83
    Activations Density 0.046%

    No Known Activations