© 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. 25089
    Prev
    Next
    INDEX
    Explanations

    references to corporations

    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
    269
    +0.16
    0.9%
    18
    +0.12
    0.7%
    499
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    269
    +0.16
    0.01
    18
    +0.12
    0.01
    174
    +0.11
    0.01
    Negative Logits
    ´
    -2.34
    ¼
    -2.21
    ¬
    -2.15
    ¿½
    -2.12
    Į
    -1.99
    ¢
    -1.98
    ij
    -1.93
    ĥ
    -1.92
    Ĺ
    -1.86
    º
    -1.84
    POSITIVE LOGITS
    finder
    2.02
    ician
    1.83
    arity
    1.83
    adic
    1.80
    ifold
    1.74
    imeter
    1.69
    ulence
    1.67
    osity
    1.65
    ovsky
    1.61
    ière
    1.60
    Activations Density 0.007%

    No Known Activations