© 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. 0-MLP-SM
    11. 26185
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental pollutants and contaminants

    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/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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    156
    +0.15
    0.8%
    124
    +0.12
    0.7%
    467
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.15
    0.02
    319
    +0.12
    0.01
    24
    +0.12
    0.02
    Negative Logits
     respects
    -1.44
    empre
    -1.43
     Version
    -1.40
    ŀ
    -1.40
     0000000000000000000000000000000000
    -1.40
    rength
    -1.40
     Province
    -1.38
    indows
    -1.37
     directions
    -1.37
    ords
    -1.37
    POSITIVE LOGITS
     onto
    1.51
    mine
    1.48
     began
    1.45
    yline
    1.42
     synthase
    1.38
     creatinine
    1.37
     exposure
    1.36
    creen
    1.36
     oneself
    1.35
    ter
    1.35
    Activations Density 0.043%

    No Known Activations