© 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. 26638
    Prev
    Next
    INDEX
    Explanations

    the color cyan in various contexts

    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
    410
    +0.15
    0.8%
    111
    +0.14
    0.8%
    369
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.15
    0.01
    111
    +0.14
    0.01
    443
    +0.12
    0.01
    Negative Logits
    rees
    -1.85
     sino
    -1.65
    illance
    -1.60
     treating
    -1.58
    plasia
    -1.46
     thereon
    -1.38
    xy
    -1.37
     Later
    -1.36
    OLOR
    -1.31
    zione
    -1.27
    POSITIVE LOGITS
    ¡
    2.29
    Ĵ
    2.04
    ²
    1.97
    ¥
    1.94
    Ģ
    1.94
    ī
    1.93
    ŀ
    1.92
    Ł
    1.90
    ł
    1.90
    ¿½
    1.86
    Activations Density 0.075%

    No Known Activations