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. 6-RES-JB
    6. 9080
    Prev
    Next
    INDEX
    Explanations

    information related to cycling competitions such as the Tour de France and specific cyclists

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.13
    0.5%
    164
    +0.08
    0.3%
    690
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1936
    +0.13
    0.03
    722
    +0.08
    0.04
    112
    +0.08
    0.04
    Negative Logits
    <bos>
    -2.61
    contentLoaded
    -0.78
     initComponents
    -0.78
     Paglinawan
    -0.75
    getClassLoader
    -0.72
    
    
    -0.71
    InjectAttribute
    -0.69
    ExtendWith
    -0.68
    PerformLayout
    -0.68
    didSet
    -0.67
    POSITIVE LOGITS
     Juf
    1.62
     increa
    1.61
     stockholm
    1.56
     maneu
    1.54
     aen
    1.51
     fortn
    1.48
     fta
    1.48
     affor
    1.48
     panama
    1.46
     impra
    1.45
    Activations Density 0.318%

    No Known Activations