© 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. 24966
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the frequency or instances of events

    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
    376
    +0.16
    0.9%
    156
    +0.14
    0.8%
    39
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    39
    +0.16
    0.01
    471
    +0.14
    0.01
    498
    +0.10
    0.01
    Negative Logits
    ĥ½
    -2.90
    Ħ
    -2.80
    ¸
    -2.71
    ĨĴ
    -2.68
    »¿
    -2.61
    İ
    -2.61
    Į
    -2.58
    Ļª
    -2.56
    į
    -2.56
    º
    -2.53
    POSITIVE LOGITS
    ional
    1.91
    hole
    1.77
    arily
    1.77
    ball
    1.67
    ont
    1.65
    line
    1.63
     (\<
    1.61
    grounds
    1.59
    ionale
    1.58
     means
    1.55
    Activations Density 0.004%

    No Known Activations