© 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. 31207
    Prev
    Next
    INDEX
    Explanations

    words related to improving or enhancing physical strength or resilience

    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
    +0.30
    1.8%
    317
    +0.15
    0.9%
    376
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    317
    +0.30
    0.03
    156
    +0.15
    0.02
    411
    +0.14
    0.02
    Negative Logits
    Reviewer
    -1.56
    openh
    -1.49
    że
    -1.48
    rue
    -1.47
    ween
    -1.44
    awa
    -1.43
    cribe
    -1.34
    ty
    -1.34
    же
    -1.34
     Holocaust
    -1.33
    POSITIVE LOGITS
    ments
    1.77
    ĻĤ
    1.68
    stituted
    1.65
    ally
    1.52
    inely
    1.49
     jaws
    1.48
    onds
    1.44
    ations
    1.43
    idan
    1.42
    idone
    1.42
    Activations Density 0.061%

    No Known Activations