© 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. 22566
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "some" in various contexts

    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
    395
    +0.11
    0.6%
    405
    +0.10
    0.6%
    370
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.11
    0.04
    282
    +0.10
    0.03
    14
    +0.10
    0.03
    Negative Logits
     inherit
    -1.59
     SHA
    -1.45
     BSD
    -1.43
    vdots
    -1.41
     PhD
    -1.36
    teenth
    -1.34
    hew
    -1.32
     any
    -1.30
     pronounce
    -1.30
    romycin
    -1.30
    POSITIVE LOGITS
    »
    4.32
    ¼
    3.92
    Ĭ
    3.86
    Ķ
    3.81
    İ
    3.72
    ł
    3.72
    ¹
    3.69
    ı
    3.63
    č↵
    3.61
    3.61
    Activations Density 0.086%

    No Known Activations