© 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. 24991
    Prev
    Next
    INDEX
    Explanations

    references to specific dates

    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
    81
    +0.12
    0.7%
    328
    +0.11
    0.6%
    287
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    328
    +0.12
    0.02
    287
    +0.11
    0.02
    263
    +0.11
    0.02
    Negative Logits
     latter
    -2.10
     judgment
    -1.73
    ¦
    -1.70
     consequences
    -1.67
     hers
    -1.66
    ·¸
    -1.52
    °
    -1.51
     implications
    -1.47
     correctness
    -1.46
     full
    -1.45
    POSITIVE LOGITS
    ibase
    2.11
    etable
    2.03
    uet
    1.90
    upt
    1.89
    inte
    1.84
    avo
    1.80
    isión
    1.80
    ared
    1.78
    enos
    1.76
    ielsen
    1.70
    Activations Density 0.011%

    No Known Activations