© 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. 31155
    Prev
    Next
    INDEX
    Explanations

    instances of the word "I."

    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
    180
    +0.12
    0.6%
    435
    +0.11
    0.6%
    263
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    171
    +0.12
    0.17
    242
    +0.11
    0.17
    299
    +0.10
    0.16
    Negative Logits
    Ħ
    -2.27
    ī
    -2.15
    ¼
    -2.06
    ł
    -2.04
    Į
    -2.03
    ģ
    -2.00
    ĭ
    -1.97
    ¯
    -1.89
    «
    -1.82
    ^](#
    -1.80
    POSITIVE LOGITS
     dots
    1.83
     Inn
    1.58
    hire
    1.51
     eternity
    1.47
     fine
    1.42
    .","
    1.39
     childhood
    1.39
     nature
    1.38
    ://
    1.36
     herself
    1.33
    Activations Density 0.417%

    No Known Activations