© 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. 31253
    Prev
    Next
    INDEX
    Explanations

    instances of the notation "Pl" likely related to product versions or listings

    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
    477
    +0.15
    0.8%
    377
    +0.14
    0.8%
    376
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    240
    +0.15
    0.04
    476
    +0.14
    0.03
    411
    +0.14
    0.03
    Negative Logits
    tern
    -1.75
    ÑĤÑĮ
    -1.64
    nez
    -1.62
    rian
    -1.58
    rile
    -1.54
    ities
    -1.53
    izability
    -1.51
     sexes
    -1.50
     slightest
    -1.49
    lasses
    -1.49
    POSITIVE LOGITS
    gate
    1.71
    houses
    1.58
     screens
    1.56
    acements
    1.56
    acco
    1.49
    enum
    1.48
    ,[@
    1.47
    ieux
    1.45
    eval
    1.42
    adder
    1.41
    Activations Density 1.581%

    No Known Activations