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. 173
    Prev
    Next
    INDEX
    Explanations

    terms related to sports results and game outcomes

    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
    +0.31
    1.1%
    1870
    +0.13
    0.5%
    1177
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.31
    0.05
    1870
    +0.13
    0.04
    332
    +0.08
    0.05
    Negative Logits
    <bos>
    -1.35
     anse
    -0.90
     solidar
    -0.86
     aquare
    -0.85
     utop
    -0.80
     vola
    -0.80
     liker
    -0.78
     stiller
    -0.78
    ⓧ
    -0.77
     demen
    -0.76
    POSITIVE LOGITS
     soulign
    0.75
     pamph
    0.72
     heapq
    0.69
    Controversy
    0.68
     soigneusement
    0.68
     spécialement
    0.66
     semblables
    0.65
     against
    0.65
     accordé
    0.64
     Frenchmen
    0.64
    Activations Density 0.357%

    No Known Activations