© 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. 22461
    Prev
    Next
    INDEX
    Explanations

    HTML tags and their formatting

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.27
    1.5%
    454
    +0.12
    0.7%
    47
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    391
    +0.27
    0.04
    474
    +0.12
    0.02
    121
    +0.12
    0.02
    Negative Logits
    IJ
    -3.74
    ı
    -3.72
    Ĭ
    -3.72
    -3.67
    ↵↵
    -3.67
    ↵  ↵
    -3.67
    -3.67
    ↵↵↵
    -3.67
    ↵
    -3.67
    ↵
    -3.67
    POSITIVE LOGITS
    abouts
    1.60
     life
    1.44
     moderate
    1.43
    constant
    1.41
    cens
    1.40
     slow
    1.39
     sudden
    1.36
    cas
    1.31
     death
    1.31
    Scal
    1.30
    Activations Density 0.168%

    No Known Activations