© 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. 2-MLP-SM
    11. 22712
    Prev
    Next
    INDEX
    Explanations

    elements related to cellular signaling pathways and their regulation

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    502
    +0.10
    0.5%
    122
    +0.10
    0.5%
    316
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    361
    +0.10
    0.03
    410
    +0.10
    0.01
    208
    +0.09
    0.01
    Negative Logits
    Ĺ
    -3.83
    ŀ
    -3.71
    ľĵ
    -3.71
    Ģ
    -3.70
    ¡
    -3.61
    ķ
    -3.60
    Ŀ
    -3.53
    Ł
    -3.48
    ļ
    -3.47
    ĩ
    -3.47
    POSITIVE LOGITS
     arrived
    1.74
    bered
    1.59
     ADVIS
    1.47
     testified
    1.46
    unnumbered
    1.45
     omissions
    1.42
    oby
    1.42
     addressed
    1.42
     deported
    1.37
     tard
    1.36
    Activations Density 0.244%

    No Known Activations