© 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. 31133
    Prev
    Next
    INDEX
    Explanations

    words that denote various specialist professionals in scientific and legal fields

    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
    156
    +0.18
    1.1%
    224
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.18
    0.02
    323
    +0.12
    0.02
    102
    +0.11
    0.01
    Negative Logits
    ¬
    -1.90
     closed
    -1.66
    nt
    -1.61
     native
    -1.57
     therefore
    -1.54
    ĥ½
    -1.53
    hed
    -1.49
     literal
    -1.49
     relation
    -1.48
    hing
    -1.45
    POSITIVE LOGITS
     contender
    1.83
    aho
    1.78
    iste
    1.77
    sheet
    1.75
    olta
    1.75
    naire
    1.72
    ÃŃa
    1.72
    OPLE
    1.71
    ielle
    1.71
    ista
    1.70
    Activations Density 0.015%

    No Known Activations