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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 2815
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency and effectiveness in processes and systems

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1379
    +0.12
    0.4%
    1870
    +0.11
    0.4%
    1323
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1379
    +0.12
    0.02
    241
    +0.11
    0.02
    410
    +0.11
    0.02
    Negative Logits
     accla
    -1.54
     increa
    -1.48
     exorbit
    -1.47
     reluct
    -1.47
     shenan
    -1.44
     inconce
    -1.43
     disgra
    -1.43
     indestru
    -1.42
     affor
    -1.41
     impra
    -1.38
    POSITIVE LOGITS
     efficiency
    1.43
    efficiency
    1.30
     Efficiency
    1.30
     efficient
    1.29
    efficient
    1.28
     efficiencies
    1.25
    fficiencies
    1.23
    Efficiency
    1.14
     Efficient
    1.08
    Efficient
    1.02
    Activations Density 0.078%

    No Known Activations