© 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. 31203
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "ores."

    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%
    153
    +0.11
    0.7%
    376
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.13
    0.01
    504
    +0.11
    0.01
    52
    +0.11
    0.01
    Negative Logits
    opy
    -1.75
    TY
    -1.75
     forbidden
    -1.60
     ?"
    -1.58
     least
    -1.55
     shame
    -1.52
     nature
    -1.48
    ?'
    -1.44
    ))$.
    -1.42
     ");
    -1.41
    POSITIVE LOGITS
    pora
    2.13
    eries
    2.00
    ista
    1.86
    enos
    1.86
     genre
    1.81
    hoe
    1.76
    heet
    1.75
    pire
    1.74
    pad
    1.71
    piration
    1.68
    Activations Density 0.016%

    No Known Activations