© 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. 30023
    Prev
    Next
    INDEX
    Explanations

    references to a specific brand or company name

    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
    376
    +0.21
    1.2%
    203
    +0.15
    0.8%
    369
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.21
    0.01
    367
    +0.15
    0.01
    203
    +0.13
    0.01
    Negative Logits
    cknowled
    -1.61
    oxacin
    -1.61
     third
    -1.49
    imab
    -1.49
    izability
    -1.46
    ---|---|---
    -1.43
    rimination
    -1.42
    effectiveness
    -1.40
    ization
    -1.39
    acial
    -1.38
    POSITIVE LOGITS
    ģ
    2.95
    į
    2.86
    ±
    2.84
    Ĵ
    2.83
    ¥
    2.73
    ĸ
    2.70
    Ĭ
    2.67
    ī
    2.65
    Į
    2.63
    º
    2.62
    Activations Density 0.012%

    No Known Activations