© 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. 25067
    Prev
    Next
    INDEX
    Explanations

    technical terms related to network connections

    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
    +0.17
    1.0%
    156
    +0.12
    0.7%
    181
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.17
    0.01
    158
    +0.12
    0.01
    232
    +0.12
    0.01
    Negative Logits
    oles
    -1.92
    ĥ½
    -1.88
    rocyte
    -1.61
     certain
    -1.60
    rogens
    -1.60
    "?"
    -1.59
     thou
    -1.56
    olate
    -1.54
    ?”
    -1.53
     what
    -1.50
    POSITIVE LOGITS
    notes
    1.84
    wright
    1.79
    shock
    1.74
    ally
    1.68
    aho
    1.60
    gap
    1.57
    break
    1.57
    naire
    1.55
    Stats
    1.51
    igan
    1.50
    Activations Density 0.016%

    No Known Activations