© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 23694
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and associated treatments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/2-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.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.29
    1.6%
    478
    +0.19
    1.1%
    332
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.29
    0.06
    478
    +0.19
    0.09
    410
    +0.10
    0.03
    Negative Logits
    works
    -1.96
    iers
    -1.89
    charts
    -1.84
    chains
    -1.84
    NOTES
    -1.75
    ière
    -1.73
    -
    -1.72
    prises
    -1.68
    ström
    -1.68
    makers
    -1.63
    POSITIVE LOGITS
     tears
    1.65
     upset
    1.56
    athe
    1.54
     satisfied
    1.53
     amazed
    1.51
     pleased
    1.49
     heartbeat
    1.49
     happy
    1.47
     else
    1.46
     Deaf
    1.44
    Activations Density 0.570%

    No Known Activations