© 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. 29884
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "as."

    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
    511
    +0.12
    0.7%
    13
    +0.12
    0.7%
    310
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.12
    0.17
    502
    +0.12
    0.14
    479
    +0.12
    0.15
    Negative Logits
     states
    -1.58
     loved
    -1.48
     assigned
    -1.45
     orders
    -1.43
     office
    -1.43
    otted
    -1.42
     DFT
    -1.42
    holders
    -1.38
     inbox
    -1.34
    uties
    -1.33
    POSITIVE LOGITS
    oda
    1.81
    º
    1.68
    akia
    1.67
    ¦
    1.66
    oha
    1.63
    ĺ
    1.59
    odus
    1.56
    ĸ
    1.54
    ¼
    1.54
    apa
    1.51
    Activations Density 0.321%

    No Known Activations