© 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. 25182
    Prev
    Next
    INDEX
    Explanations

    references to the year 1996

    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
    142
    +0.13
    0.7%
    249
    +0.13
    0.7%
    436
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.13
    0.02
    238
    +0.13
    0.02
    249
    +0.12
    0.02
    Negative Logits
    ights
    -1.60
     suspicion
    -1.58
    hores
    -1.57
     retaliation
    -1.55
     conscience
    -1.51
    ls
    -1.49
     lib
    -1.48
     strict
    -1.48
     latter
    -1.47
     favor
    -1.46
    POSITIVE LOGITS
    icolor
    2.03
    zilla
    1.71
    ERTY
    1.64
    ental
    1.64
    ZX
    1.60
    argin
    1.57
    ourier
    1.56
    olecule
    1.55
    nai
    1.54
     anniversary
    1.52
    Activations Density 0.571%

    No Known Activations