© 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. 25044
    Prev
    Next
    INDEX
    Explanations

    references to mediocrity

    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
    111
    +0.11
    0.6%
    485
    +0.11
    0.6%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.11
    0.01
    111
    +0.11
    0.01
    427
    +0.11
    0.01
    Negative Logits
    )){
    -1.83
    tis
    -1.70
    nel
    -1.59
     precious
    -1.58
    edes
    -1.58
     Coming
    -1.55
    terday
    -1.48
     same
    -1.48
     Come
    -1.46
    cross
    -1.45
    POSITIVE LOGITS
    ¹
    3.18
    º
    3.00
    ĻĤ
    2.96
    Īĺ
    2.88
    ¿
    2.81
    2.72
    ↵
    2.72
    ↵
    2.72
    2.72
    2.72
    Activations Density 0.115%

    No Known Activations