© 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. 31248
    Prev
    Next
    INDEX
    Explanations

    fields or variables in code structures

    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
    391
    +0.13
    0.8%
    217
    +0.12
    0.7%
    380
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.13
    0.02
    380
    +0.12
    0.02
    389
    +0.12
    0.02
    Negative Logits
    then
    -1.86
    )](#
    -1.72
    ]>
    -1.69
    radiol
    -1.65
     nothing
    -1.62
    Ĥ
    -1.61
     a
    -1.57
     suppose
    -1.56
     an
    -1.53
    ³
    -1.51
    POSITIVE LOGITS
    yards
    2.35
    notes
    2.22
    yard
    2.21
    gren
    2.15
    cias
    2.01
    ière
    2.00
    heim
    1.99
    ings
    1.95
    nement
    1.87
    work
    1.86
    Activations Density 0.016%

    No Known Activations