© 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. 30996
    Prev
    Next
    INDEX
    Explanations

    references to relational connections or strong preferences

    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
    1.2%
    72
    +0.13
    0.8%
    71
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    320
    +0.20
    0.01
    72
    +0.13
    0.01
    232
    +0.12
    0.01
    Negative Logits
    ±
    -2.42
    ĨĴ
    -2.37
    ´
    -2.36
    ¯
    -2.33
    ĸ´
    -2.30
    Ļª
    -2.27
    ¿
    -2.16
    ¸
    -2.16
    »
    -2.15
    º
    -2.15
    POSITIVE LOGITS
     chambers
    1.74
     chromatography
    1.62
    AtIndex
    1.59
     \-
    1.55
    PCR
    1.54
    wise
    1.50
    {}{
    1.50
     chamber
    1.48
     guard
    1.47
    port
    1.43
    Activations Density 0.014%

    No Known Activations