© 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. 22383
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and elements related to web development

    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
    258
    +0.12
    0.7%
    23
    +0.11
    0.6%
    381
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.12
    0.03
    56
    +0.11
    0.05
    458
    +0.11
    0.03
    Negative Logits
    º
    -3.97
    Ħ
    -3.73
    ¿½
    -3.65
    <|outofrange|>
    -3.65
    -3.65
    ↵↵
    -3.65
    ↵↵
    -3.65
    <|outofrange|>
    -3.65
    -3.65
    ↵
    -3.65
    POSITIVE LOGITS
     messenger
    1.73
    inx
    1.60
    issa
    1.58
     silence
    1.57
    yline
    1.55
     delegates
    1.50
     beneficiaries
    1.49
    iline
    1.48
    il
    1.48
     monarch
    1.46
    Activations Density 0.362%

    No Known Activations