© 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. 31014
    Prev
    Next
    INDEX
    Explanations

    terms related to external influences

    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%
    471
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    471
    +0.16
    0.01
    268
    +0.14
    0.01
    31
    +0.12
    0.01
    Negative Logits
    ¿½
    -1.60
    §
    -1.52
     trusts
    -1.50
    ÄŁ
    -1.48
     preponderance
    -1.48
     Trust
    -1.47
    atchewan
    -1.46
    'll
    -1.46
    bs
    -1.46
    atinib
    -1.44
    POSITIVE LOGITS
    hell
    1.93
    heet
    1.73
    omal
    1.65
    how
    1.58
    ize
    1.44
     crop
    1.42
    helf
    1.39
    ome
    1.37
    idium
    1.37
    idan
    1.34
    Activations Density 0.033%

    No Known Activations