© 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. 0-MLP-SM
    11. 31142
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" and its associated frequency in the context of learning and development

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    478
    +0.30
    1.9%
    98
    +0.22
    1.4%
    23
    +0.21
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.30
    0.25
    98
    +0.22
    0.13
    139
    +0.21
    0.21
    Negative Logits
    heads
    -1.87
    ment
    -1.82
    ingly
    -1.80
    oque
    -1.76
    wise
    -1.68
    irl
    -1.67
    isters
    -1.67
    isme
    -1.64
     (,
    -1.64
    borg
    -1.63
    POSITIVE LOGITS
     order
    2.53
     vivo
    2.50
     particular
    2.49
    ·¸
    2.48
    ĻĤ
    2.46
     spite
    2.45
    Ĭ
    2.44
     vitro
    2.34
     conjunction
    2.34
    Ĥ
    2.29
    Activations Density 0.996%

    No Known Activations