© 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. 31165
    Prev
    Next
    INDEX
    Explanations

    instances of the word "either."

    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
    353
    +0.13
    0.7%
    325
    +0.12
    0.6%
    470
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.13
    0.06
    325
    +0.12
    0.04
    387
    +0.11
    0.04
    Negative Logits
    ľĵ
    -1.59
    Ħ
    -1.50
    ĵ
    -1.49
    Bean
    -1.45
    én
    -1.42
    ¦
    -1.38
    ids
    -1.37
     lad
    -1.37
    Listener
    -1.35
    ©
    -1.35
    POSITIVE LOGITS
    abouts
    1.82
    chitz
    1.60
     chambers
    1.51
    ril
    1.48
    rendum
    1.45
    etine
    1.43
    rops
    1.40
     prints
    1.39
     suicidal
    1.37
    iom
    1.34
    Activations Density 0.690%

    No Known Activations