© 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. 28837
    Prev
    Next
    INDEX
    Explanations

    the word "To" indicating actions or instructions

    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
    38
    +0.13
    0.7%
    197
    +0.12
    0.6%
    241
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.13
    0.04
    431
    +0.12
    0.03
    389
    +0.11
    0.03
    Negative Logits
    áĢ¬
    -1.89
    à±ģ
    -1.69
    à°¿
    -1.69
    quier
    -1.62
    Õ¡
    -1.62
    Õ¡Õ
    -1.60
    áĢIJ
    -1.60
    ા
    -1.59
    áĢ¸
    -1.57
    ÖĢ
    -1.54
    POSITIVE LOGITS
    documentclass
    1.98
     coherence
    1.50
    kw
    1.46
     Stark
    1.41
    opsis
    1.34
    TD
    1.34
    **_
    1.34
    Fer
    1.33
    amento
    1.32
     df
    1.32
    Activations Density 0.017%

    No Known Activations