© 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. 2-MLP-SM
    11. 22574
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fall" in various forms

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    428
    +0.13
    0.7%
    43
    +0.12
    0.6%
    299
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    299
    +0.13
    0.02
    411
    +0.12
    0.02
    428
    +0.12
    0.03
    Negative Logits
    ctin
    -1.77
    ordin
    -1.70
    Argued
    -1.69
    kubuntu
    -1.53
    fts
    -1.44
    freak
    -1.42
    trl
    -1.41
    ollar
    -1.40
    zk
    -1.40
    Submitted
    -1.40
    POSITIVE LOGITS
    eness
    1.56
    icism
    1.46
    ī
    1.40
     tumour
    1.36
    inian
    1.34
    inus
    1.33
     incision
    1.33
     Polymer
    1.29
    icle
    1.28
    inic
    1.28
    Activations Density 0.318%

    No Known Activations