© 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. 30893
    Prev
    Next
    INDEX
    Explanations

    specific time-related references or durations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.14
    0.8%
    293
    +0.13
    0.8%
    144
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.14
    0.01
    108
    +0.13
    0.01
    378
    +0.12
    0.01
    Negative Logits
    agers
    -1.70
    )\].
    -1.67
     night
    -1.61
     prayer
    -1.46
     transgender
    -1.45
     quit
    -1.45
    )\]
    -1.44
     discriminated
    -1.43
    idays
    -1.39
    athing
    -1.39
    POSITIVE LOGITS
    core
    2.09
    cores
    2.09
    aurus
    1.74
    iella
    1.73
    creen
    1.72
    icum
    1.72
    pot
    1.71
    ium
    1.70
    bilt
    1.65
    eries
    1.57
    Activations Density 0.010%

    No Known Activations