© 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. 25099
    Prev
    Next
    INDEX
    Explanations

    repeated references to a graphical element or container in a coding context

    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
    217
    +0.12
    0.7%
    397
    +0.10
    0.6%
    392
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    66
    +0.12
    0.02
    3
    +0.10
    0.01
    217
    +0.10
    0.01
    Negative Logits
     yours
    -1.89
     lack
    -1.83
    '?"
    -1.80
     vain
    -1.75
     brow
    -1.74
     hers
    -1.65
     distance
    -1.64
    "?"
    -1.63
     ?"
    -1.63
     afraid
    -1.63
    POSITIVE LOGITS
    plots
    2.40
    erior
    2.30
    enstein
    2.30
    krit
    2.07
    vist
    1.91
    ing
    1.89
    er
    1.85
    erne
    1.84
    anguage
    1.83
    pool
    1.82
    Activations Density 0.008%

    No Known Activations