© 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. 31241
    Prev
    Next
    INDEX
    Explanations

    terms related to null values and memory management in programming

    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
    238
    +0.16
    0.9%
    100
    +0.14
    0.8%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.16
    0.03
    320
    +0.14
    0.02
    490
    +0.13
    0.02
    Negative Logits
     stimulating
    -1.52
    ↵
    -1.52
     fact
    -1.47
    ]{}]{}
    -1.45
     indeed
    -1.41
    matically
    -1.41
    building
    -1.37
    ↵
    -1.36
    ometer
    -1.35
     tailor
    -1.33
    POSITIVE LOGITS
     weddings
    1.76
    ¥
    1.74
    ĻĤ
    1.72
    ª
    1.71
    Ļ
    1.69
    £
    1.68
    Ń
    1.68
    Īĺ
    1.68
    Ľ
    1.66
    ļ
    1.65
    Activations Density 0.019%

    No Known Activations