© 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. 31186
    Prev
    Next
    INDEX
    Explanations

    terms related to athleticism and support 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
    +0.23
    1.3%
    23
    +0.17
    1.0%
    82
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.23
    0.03
    82
    +0.17
    0.03
    408
    +0.16
    0.02
    Negative Logits
    esan
    -1.66
    orman
    -1.62
    ionate
    -1.56
    uelle
    -1.56
    rente
    -1.55
    iver
    -1.54
    aul
    -1.49
    chitz
    -1.46
    owa
    -1.43
    eful
    -1.40
    POSITIVE LOGITS
    µ
    2.44
    Ĥ¬
    2.28
    ities
    2.23
    Ĥ
    2.17
    Īĺ
    2.14
    ¢
    2.08
    ľĵ
    2.07
    ĥ
    2.00
    Ħ
    1.98
    ³
    1.93
    Activations Density 0.045%

    No Known Activations