© 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. 31049
    Prev
    Next
    INDEX
    Explanations

    the word "ion"

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    177
    +0.13
    0.7%
    232
    +0.12
    0.7%
    118
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.13
    0.03
    232
    +0.12
    0.02
    177
    +0.12
    0.02
    Negative Logits
     anything
    -1.66
    ances
    -1.63
     existence
    -1.62
    soever
    -1.62
    irth
    -1.61
    ãĤĥ
    -1.53
    inners
    -1.50
    "?"
    -1.47
     said
    -1.45
    omitempty
    -1.42
    POSITIVE LOGITS
    naire
    1.97
    ista
    1.95
    cias
    1.94
    heim
    1.92
    kowski
    1.81
    istas
    1.80
    etes
    1.74
    cript
    1.72
    etto
    1.72
    etable
    1.71
    Activations Density 0.532%

    No Known Activations