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. 12-RES-JB
    6. 7853
    Prev
    Next
    INDEX
    Explanations

    references to jet-setting and air travel

    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.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    1.3%
    650
    +0.12
    0.6%
    316
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1895
    +0.24
    0.01
    662
    +0.12
    0.01
    316
    +0.11
    0.01
    Negative Logits
    <bos>
    -2.04
    makeConstraints
    -0.62
     يتيمه
    -0.59
     AssemblyCompany
    -0.57
     وتسجيلات
    -0.57
    PerformLayout
    -0.54
    CreateMap
    -0.53
    //---
    -0.53
    BagLayout
    -0.52
     comprehend
    -0.52
    POSITIVE LOGITS
     jet
    1.30
     Jet
    1.29
    Jet
    1.18
     jets
    1.14
     Jets
    1.13
    Jets
    1.09
    jet
    1.08
     JET
    1.04
    jetty
    1.02
     ejus
    0.98
    Activations Density 0.033%

    No Known Activations