© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28796
    Prev
    Next
    INDEX
    Explanations

    instances of the word "the"

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    178
    +0.15
    0.8%
    348
    +0.15
    0.8%
    97
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.15
    0.48
    98
    +0.15
    0.21
    228
    +0.13
    0.32
    Negative Logits
    °
    -2.57
    ¥
    -2.56
    İ
    -2.35
    ĥ½
    -2.27
    ģ
    -2.25
    ↵
    -2.23
    ↵  âĢĥ
    -2.23
          ↵
    -2.23
    ↵
    -2.23
    č↵
    -2.23
    POSITIVE LOGITS
    etin
    1.79
    juvant
    1.63
    ji
    1.53
     equivalents
    1.53
    ruct
    1.52
     counterparts
    1.46
    MSCs
    1.41
    rong
    1.41
    za
    1.38
    ${
    1.36
    Activations Density 2.904%

    No Known Activations