© 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. 31242
    Prev
    Next
    INDEX
    Explanations

    instances of the word "table" in various contexts

    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
    117
    +0.12
    0.7%
    224
    +0.11
    0.6%
    466
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.12
    0.03
    378
    +0.11
    0.02
    347
    +0.10
    0.02
    Negative Logits
    soever
    -1.75
    ³
    -1.67
    rogens
    -1.53
     Flynn
    -1.38
    yy
    -1.37
    Ļª
    -1.37
     way
    -1.36
    oles
    -1.36
    ness
    -1.35
    .'
    -1.35
    POSITIVE LOGITS
    lists
    2.16
    notes
    1.87
    iff
    1.87
    holder
    1.83
    cloth
    1.73
    ball
    1.72
    note
    1.68
    ius
    1.60
    listing
    1.58
    imetric
    1.56
    Activations Density 0.011%

    No Known Activations