© 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. 24952
    Prev
    Next
    INDEX
    Explanations

    references to the term "NE"

    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
    369
    +0.14
    0.8%
    334
    +0.14
    0.8%
    232
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.14
    0.01
    419
    +0.14
    0.01
    232
    +0.13
    0.01
    Negative Logits
    rian
    -1.93
     myself
    -1.87
    nered
    -1.83
    nez
    -1.73
    uppose
    -1.59
    hed
    -1.50
     full
    -1.49
    opause
    -1.48
    tering
    -1.47
    here
    -1.45
    POSITIVE LOGITS
    tech
    1.61
    swer
    1.49
    WL
    1.49
     (“
    1.47
    scape
    1.47
     niche
    1.42
    ÅĽci
    1.42
     alc
    1.42
     wordt
    1.41
     pockets
    1.41
    Activations Density 0.006%

    No Known Activations