© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 22571
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and symbols

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    217
    +0.17
    0.9%
    465
    +0.11
    0.6%
    455
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.17
    0.10
    505
    +0.11
    0.06
    465
    +0.11
    0.08
    Negative Logits
    Ļª
    -5.38
    ķ
    -5.36
    ¿
    -5.31
       ↵
    -5.21
    -5.21
    ↵
    -5.21
    <|outofrange|>
    -5.21
    ↵
    -5.21
    ↵
    -5.21
          ↵
    -5.21
    POSITIVE LOGITS
    ongo
    1.86
    itsu
    1.64
    league
    1.60
    ÃŃf
    1.52
    atura
    1.51
    ÃŃa
    1.48
    bean
    1.45
    emos
    1.44
    beans
    1.43
    ului
    1.41
    Activations Density 0.954%

    No Known Activations