© 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. 24015
    Prev
    Next
    INDEX
    Explanations

    medical terms and numerical data related to health conditions

    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
    98
    +0.12
    0.7%
    419
    +0.12
    0.7%
    384
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    376
    +0.12
    0.07
    421
    +0.12
    0.07
    364
    +0.11
    0.06
    Negative Logits
    -6.40
    č↵
    -6.40
     ↵
    -6.40
    -6.40
    -6.40
    -6.40
    ↵
    -6.40
    -6.40
              ↵
    -6.40
    -6.40
    POSITIVE LOGITS
    leman
    1.61
    buntu
    1.60
     pertains
    1.56
    hardt
    1.55
     Liqu
    1.43
     ourselves
    1.41
    wan
    1.41
     Fed
    1.41
    prises
    1.40
    inj
    1.40
    Activations Density 0.157%

    No Known Activations