© 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. 31135
    Prev
    Next
    INDEX
    Explanations

    references to defense-related topics or entities

    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
    156
    +0.13
    0.7%
    369
    +0.13
    0.7%
    439
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.13
    0.03
    271
    +0.13
    0.01
    56
    +0.12
    0.01
    Negative Logits
    ĥ½
    -2.76
    ı
    -2.39
    ĭ
    -1.85
    ¸
    -1.84
    Ĵ
    -1.84
    ¯
    -1.83
    ±
    -1.80
    ķ
    -1.69
    Ĭ
    -1.68
     forth
    -1.63
    POSITIVE LOGITS
    zone
    1.71
    minster
    1.67
    !=
    1.58
    check
    1.54
    runner
    1.48
    smen
    1.45
    break
    1.45
    needs
    1.43
    nier
    1.41
     Academy
    1.40
    Activations Density 3.606%

    No Known Activations