© 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. 25131
    Prev
    Next
    INDEX
    Explanations

    attributes related to adaptability or flexibility 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
    156
    +0.37
    2.2%
    376
    +0.15
    0.9%
    148
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.37
    0.01
    438
    +0.15
    0.01
    346
    +0.13
    0.01
    Negative Logits
    ori
    -1.42
    *\*
    -1.38
    lev
    -1.32
    +$
    -1.28
    uras
    -1.26
    arte
    -1.24
    âĢIJ
    -1.22
    ostatin
    -1.21
    *)
    -1.20
    :/
    -1.20
    POSITIVE LOGITS
    ¼
    3.98
    Īĺ
    3.94
    ¿½
    3.89
    Ł
    3.85
    ł
    3.85
    ģ
    3.82
    ª
    3.79
    ľĵ
    3.79
    ¢
    3.77
    Ĥ
    3.75
    Activations Density 0.010%

    No Known Activations