© 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. 23844
    Prev
    Next
    INDEX
    Explanations

    concepts related to prevention and health management strategies

    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
    401
    +0.12
    0.7%
    404
    +0.12
    0.7%
    273
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.12
    0.11
    155
    +0.12
    0.10
    55
    +0.11
    0.05
    Negative Logits
    ĻĤ
    -3.16
    Ļ
    -2.71
    ŀ
    -2.57
    ´
    -2.37
    ı
    -2.36
    ł
    -2.36
    »¿
    -2.34
    ģ
    -2.34
    ¦
    -2.34
    ¿
    -2.31
    POSITIVE LOGITS
    forge
    1.73
    odge
    1.56
     mailing
    1.53
     abroad
    1.51
     cruise
    1.51
     commission
    1.50
    paper
    1.49
    intern
    1.47
    ?”
    1.47
    arynge
    1.44
    Activations Density 1.327%

    No Known Activations