© 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. 31148
    Prev
    Next
    INDEX
    Explanations

    instances of the word "on."

    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
    229
    +0.14
    0.8%
    455
    +0.14
    0.8%
    475
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.21
    152
    +0.14
    0.17
    47
    +0.12
    0.15
    Negative Logits
    ľ
    -2.56
    Ĭ
    -2.49
    Ń
    -2.39
    º
    -2.37
    ·¸
    -2.27
    ĺ
    -2.26
    ł
    -2.24
    ·
    -2.23
    Ī
    -2.21
    ĭ
    -2.19
    POSITIVE LOGITS
    ths
    1.75
    ician
    1.71
    abil
    1.68
    ramento
    1.64
    iary
    1.63
     badly
    1.61
    â
    1.58
    grown
    1.56
    thia
    1.55
    street
    1.49
    Activations Density 0.437%

    No Known Activations