© 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 EvalsExportsinterp-engineNEWAPI 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. 30390
    Prev
    Next
    INDEX
    Explanations

    the word "to" used in various contexts

    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
    376
    +0.19
    1.0%
    434
    +0.11
    0.6%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.19
    0.04
    486
    +0.11
    0.04
    389
    +0.11
    0.04
    Negative Logits
     sake
    -1.79
    backs
    -1.67
    estly
    -1.59
    antly
    -1.57
    erals
    -1.53
    ãģij
    -1.52
    ãĤĥ
    -1.48
    ally
    -1.47
    icular
    -1.46
     mainly
    -1.41
    POSITIVE LOGITS
    «
    3.19
    ¬
    2.70
    ī
    2.65
    Īĺ
    2.53
      ↵
    2.51
    ª
    2.51
    2.51
    2.51
    ↵
    2.51
    ↵↵
    2.51
    Activations Density 3.569%

    No Known Activations