© 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. 24989
    Prev
    Next
    INDEX
    Explanations

    the act of listening

    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
    +0.16
    0.9%
    121
    +0.13
    0.7%
    438
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    121
    +0.16
    0.02
    334
    +0.13
    0.02
    298
    +0.12
    0.02
    Negative Logits
    ]]>
    -1.67
    ĥ½
    -1.63
    ĥ
    -1.56
    ureus
    -1.50
     fortune
    -1.49
    ·
    -1.49
    ľĵ
    -1.48
    Ĥ
    -1.48
    ```
    -1.45
    nez
    -1.44
    POSITIVE LOGITS
    ingly
    1.78
    icted
    1.78
    ÅĽci
    1.74
    ved
    1.61
    ership
    1.61
    inese
    1.57
     section
    1.55
    eting
    1.55
    casts
    1.53
    ied
    1.52
    Activations Density 0.409%

    No Known Activations