© 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. 22704
    Prev
    Next
    INDEX
    Explanations

    legal terminology and descriptive phrases in technical texts

    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
    107
    +0.10
    0.6%
    238
    +0.10
    0.6%
    508
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    461
    +0.10
    0.06
    502
    +0.10
    0.07
    238
    +0.10
    0.01
    Negative Logits
     nic
    -1.66
    rs
    -1.49
    ring
    -1.49
     clar
    -1.48
    ously
    -1.46
    ifying
    -1.40
     emph
    -1.38
     my
    -1.37
     offering
    -1.37
     pity
    -1.37
    POSITIVE LOGITS
    ↵
    3.39
    3.39
    ↵  ³³³
    3.39
    <|outofrange|>
    3.39
    ↵
    3.39
    ↵
    3.39
      ↵
    3.39
    ↵
    3.39
    ↵
    3.39
    3.39
    Activations Density 1.595%

    No Known Activations