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. 8260
    Prev
    Next
    INDEX
    Explanations

    code snippets related to setting frames per second for updating a stage in interactive web development

    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
    876
    +0.15
    0.4%
    690
    +0.12
    0.3%
    1336
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    876
    +0.15
    -0.01
    282
    +0.12
    0.03
    1819
    +0.10
    0.05
    Negative Logits
    Televis
    -0.62
    ioutil
    -0.57
    Šaltiniai
    -0.57
    conceito
    -0.56
     '\\;'
    -0.55
    <bos>
    -0.54
     للاسماء
    -0.53
     الاطلاع
    -0.52
    Selección
    -0.51
    Discografia
    -0.51
    POSITIVE LOGITS
     intersper
    1.30
     disreg
    1.02
     increa
    1.02
     hairc
    1.00
     impra
    0.98
     indestru
    0.94
     swarovski
    0.94
     stickied
    0.94
     periodicity
    0.93
     guarante
    0.93
    Activations Density 0.457%

    No Known Activations