© 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. 22516
    Prev
    Next
    INDEX
    Explanations

    specific model numbers or identifiers related to products, particularly in technology and electronics

    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
    395
    +0.13
    0.7%
    23
    +0.11
    0.6%
    109
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.13
    0.06
    82
    +0.11
    0.03
    196
    +0.11
    0.05
    Negative Logits
    »¿
    -2.00
    ģ
    -1.77
    «
    -1.75
    Ŀ
    -1.69
    ong
    -1.68
    Ļ
    -1.60
     waiver
    -1.38
    Ĩ
    -1.35
    ¾
    -1.33
    kon
    -1.33
    POSITIVE LOGITS
     yourself
    1.75
    herin
    1.49
     logarithm
    1.48
    ierno
    1.46
    rien
    1.45
     enormous
    1.36
     highest
    1.33
    ène
    1.29
    othermal
    1.28
    _"
    1.28
    Activations Density 0.399%

    No Known Activations