© 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. 31261
    Prev
    Next
    INDEX
    Explanations

    references to files within the document

    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
    +0.14
    0.8%
    224
    +0.12
    0.7%
    91
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    275
    +0.14
    0.03
    224
    +0.12
    0.03
    91
    +0.12
    0.03
    Negative Logits
     modulus
    -1.83
    itively
    -1.51
    uke
    -1.42
    енÑĤ
    -1.36
    ounder
    -1.34
    itiveness
    -1.34
     semicon
    -1.34
     toler
    -1.33
     yours
    -1.32
    yx
    -1.31
    POSITIVE LOGITS
    ĻĤ
    2.14
    illery
    1.99
    guns
    1.98
    lier
    1.95
    ball
    1.81
    istic
    1.77
    stadt
    1.74
    balls
    1.70
    zone
    1.66
    ontal
    1.64
    Activations Density 0.112%

    No Known Activations