© 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. 24994
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "on."

    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
    386
    +0.12
    0.7%
    426
    +0.12
    0.6%
    132
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.12
    0.22
    152
    +0.12
    0.17
    47
    +0.11
    0.15
    Negative Logits
    imab
    -1.89
    eer
    -1.71
    cine
    -1.59
    elves
    -1.50
     among
    -1.49
    eren
    -1.44
     yourselves
    -1.43
     amongst
    -1.42
     logarithm
    -1.42
    economic
    -1.37
    POSITIVE LOGITS
    ĥ½
    2.38
    ¢
    2.28
    Ļª
    2.16
    Ľ
    1.93
    IJ
    1.92
    ł
    1.86
    Ĵ
    1.81
    Ĥ
    1.80
    ij
    1.79
    ¾
    1.73
    Activations Density 0.446%

    No Known Activations