© 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. 24988
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a duration of time in seconds

    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
    156
    +0.17
    0.9%
    161
    +0.12
    0.7%
    494
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    161
    +0.17
    0.02
    7
    +0.12
    0.02
    120
    +0.11
    0.02
    Negative Logits
    ĥ
    -1.65
    affe
    -1.47
    ONS
    -1.44
    icin
    -1.40
    ivities
    -1.39
    ľĵ
    -1.38
    lm
    -1.37
    olesterol
    -1.35
     pleasures
    -1.33
     Books
    -1.32
    POSITIVE LOGITS
     apart
    1.76
    itate
    1.63
    enta
    1.60
    arily
    1.54
    ently
    1.54
    umber
    1.51
     elapsed
    1.47
     range
    1.46
    ontally
    1.44
     halt
    1.44
    Activations Density 0.020%

    No Known Activations