© 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. 30878
    Prev
    Next
    INDEX
    Explanations

    phrases related to positive endorsements or recommendations

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.21
    1.2%
    472
    +0.14
    0.8%
    300
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.21
    0.02
    300
    +0.14
    0.02
    296
    +0.13
    0.02
    Negative Logits
    uality
    -1.67
    isted
    -1.59
    rones
    -1.53
    hered
    -1.50
    elves
    -1.49
    mered
    -1.46
    TON
    -1.46
    AU
    -1.45
     conceived
    -1.45
    woke
    -1.44
    POSITIVE LOGITS
    edly
    1.83
    ably
    1.69
    ¢
    1.66
    atory
    1.60
    gery
    1.54
    ató
    1.49
    Ļ
    1.47
    atio
    1.45
     crus
    1.44
    iotic
    1.43
    Activations Density 0.459%

    No Known Activations