© 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. 0-MLP-SM
    11. 25244
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and related scientific terminology

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    396
    +0.15
    0.8%
    256
    +0.12
    0.7%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    71
    +0.12
    0.01
    410
    +0.11
    0.01
    Negative Logits
    uclear
    -1.94
     tears
    -1.66
     mention
    -1.63
     Parenthood
    -1.62
    ceived
    -1.55
    ONS
    -1.52
    ull
    -1.51
     Contact
    -1.50
    icky
    -1.49
    ucle
    -1.49
    POSITIVE LOGITS
    ĻĤ
    2.80
    ¢
    2.18
    ģ
    2.16
    <|outofrange|>
    2.15
    ↵↵
    2.15
    2.15
    ↵
    2.15
    ↵
    2.15
    ↵
    2.15
    <|outofrange|>
    2.15
    Activations Density 0.004%

    No Known Activations