© 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. 25080
    Prev
    Next
    INDEX
    Explanations

    instances of the term "IS"

    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
    52
    +0.13
    0.7%
    81
    +0.12
    0.7%
    105
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    105
    +0.13
    0.03
    52
    +0.12
    0.02
    383
    +0.11
    0.02
    Negative Logits
     ?"
    -1.70
     #"
    -1.50
      ↵
    -1.47
    asty
    -1.44
     thru
    -1.44
     ↵
    -1.43
     Thank
    -1.43
     sickness
    -1.42
     myself
    -1.40
     ")
    -1.39
    POSITIVE LOGITS
    CUIT
    1.86
    enza
    1.83
    arroll
    1.82
    leep
    1.80
    PECT
    1.78
    culus
    1.78
    ENTIAL
    1.71
    etto
    1.69
    olson
    1.66
    creen
    1.65
    Activations Density 0.207%

    No Known Activations