© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25322
    Prev
    Next
    INDEX
    Explanations

    search-related phrases and inquiries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    500
    +0.15
    0.8%
    28
    +0.11
    0.6%
    121
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    500
    +0.15
    0.12
    407
    +0.11
    0.18
    28
    +0.11
    0.14
    Negative Logits
    ĸ
    -1.89
    Ļª
    -1.71
    ¼
    -1.62
    ij
    -1.61
     respectively
    -1.60
    Ĵ
    -1.60
    ĻĤ
    -1.60
    gel
    -1.59
    STEM
    -1.55
    Ĺ
    -1.55
    POSITIVE LOGITS
    forge
    1.70
    :")
    1.66
    ='
    1.55
    )',
    1.55
    oft
    1.52
    "){
    1.48
    )'
    1.47
    Simplify
    1.46
     spelling
    1.45
     vow
    1.44
    Activations Density 3.277%

    No Known Activations