© 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. 25713
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Can" or "Could."

    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
    346
    +0.15
    0.8%
    267
    +0.10
    0.5%
    217
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.15
    0.03
    346
    +0.10
    0.03
    317
    +0.10
    0.02
    Negative Logits
    ↵↵
    -2.53
      ↵
    -2.53
    ↵↵
    -2.53
    -2.53
     ↵
    -2.53
    ↵↵
    -2.53
    -2.53
    ↵
    -2.53
     ↵
    -2.53
    -2.53
    POSITIVE LOGITS
    CEPT
    1.58
    PLC
    1.42
    keeping
    1.40
    imetry
    1.35
     campaigns
    1.35
    cal
    1.34
    playing
    1.33
    OLOR
    1.31
    ^{-\
    1.31
    :$
    1.30
    Activations Density 0.083%

    No Known Activations