© 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 EvalsExportsAPI 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. 24891
    Prev
    Next
    INDEX
    Explanations

    terms related to biomedical processes and reactions

    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
    +0.20
    1.1%
    420
    +0.13
    0.7%
    155
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.20
    0.03
    300
    +0.13
    0.01
    259
    +0.12
    0.01
    Negative Logits
    #.
    -1.54
    +.
    -1.47
    не
    -1.45
    chle
    -1.45
    stroke
    -1.43
    pper
    -1.40
    chanical
    -1.39
    annon
    -1.39
    âĢ¢
    -1.38
     elucid
    -1.38
    POSITIVE LOGITS
    Ļª
    3.06
    Ĺ
    2.92
    ĥ½
    2.71
    £
    2.50
    ļ
    2.35
    2.28
    ↵
    2.28
    ↵
    2.28
    č↵
    2.28
          ↵
    2.28
    Activations Density 0.076%

    No Known Activations