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

    Neuronpedia

    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. 25545
    Prev
    Next
    INDEX
    Explanations

    recipes involving comfort food and hearty dishes

    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
    407
    +0.14
    0.8%
    296
    +0.11
    0.6%
    311
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    457
    +0.14
    0.06
    118
    +0.11
    0.13
    296
    +0.11
    0.11
    Negative Logits
     taste
    -2.09
     paste
    -1.79
     baking
    -1.74
     ingredients
    -1.66
     cooking
    -1.64
     easy
    -1.61
     tastes
    -1.60
     consumption
    -1.58
     aroma
    -1.57
     neat
    -1.56
    POSITIVE LOGITS
    £
    2.50
    į
    2.38
    İ
    2.22
      ↵
    2.16
    2.16
    <|outofrange|>
    2.16
    2.16
    ↵↵
    2.16
    ↵
    2.16
    ↵
    2.16
    Activations Density 2.858%

    No Known Activations