© 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. 25172
    Prev
    Next
    INDEX
    Explanations

    references to temperature and humidity

    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
    +0.20
    1.1%
    113
    +0.13
    0.7%
    269
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    167
    +0.20
    0.03
    319
    +0.13
    0.02
    113
    +0.11
    0.02
    Negative Logits
    Ŀ
    -2.59
    ¿
    -2.51
    ĥ½
    -2.39
    Ĥ¬
    -2.38
    ł
    -2.34
    ↵
    -2.30
    -2.30
    ↵  âĢĥ
    -2.30
    ↵↵
    -2.30
    -2.30
    POSITIVE LOGITS
     rises
    1.55
    aho
    1.55
     ranges
    1.54
     tolerance
    1.52
    banks
    1.51
    Watch
    1.50
     (\>
    1.47
    IPS
    1.45
     adaptation
    1.42
     discrimination
    1.40
    Activations Density 0.016%

    No Known Activations