© 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. 31189
    Prev
    Next
    INDEX
    Explanations

    the preposition "to" and other related actions or directions

    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
    126
    +0.16
    0.9%
    485
    +0.12
    0.6%
    452
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.16
    0.44
    434
    +0.12
    0.30
    151
    +0.12
    0.26
    Negative Logits
    enia
    -1.69
    apest
    -1.61
    eva
    -1.56
    enta
    -1.55
    ¥
    -1.52
    encode
    -1.50
    mber
    -1.49
    mina
    -1.47
    {"
    -1.46
    елÑĮ
    -1.46
    POSITIVE LOGITS
     speeds
    1.72
    acle
    1.64
     Methods
    1.57
     manners
    1.48
     quantities
    1.47
     lifetime
    1.47
     bugs
    1.47
     lengths
    1.46
     layers
    1.43
    anese
    1.41
    Activations Density 2.057%

    No Known Activations