© 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. 25157
    Prev
    Next
    INDEX
    Explanations

    instances of repeated or structured data entries

    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
    11
    +0.13
    0.8%
    445
    +0.13
    0.8%
    487
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.13
    0.02
    445
    +0.13
    0.01
    334
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.17
    Ń
    -2.11
    ¥
    -2.07
    §
    -1.96
    ·¸
    -1.94
    ¿½
    -1.91
    ľ
    -1.86
     nothing
    -1.82
    "?"
    -1.70
    «
    -1.69
    POSITIVE LOGITS
    ÅĽci
    1.96
    naire
    1.81
    prising
    1.74
     mechanic
    1.70
    erior
    1.70
    quarters
    1.68
     trials
    1.63
    finder
    1.61
    bellum
    1.60
     routes
    1.59
    Activations Density 0.012%

    No Known Activations