© 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. 23911
    Prev
    Next
    INDEX
    Explanations

    topics related to environmental impact and management, particularly concerning water quality and pollution

    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
    296
    +0.14
    0.7%
    379
    +0.13
    0.7%
    39
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    296
    +0.14
    0.09
    160
    +0.13
    0.10
    410
    +0.12
    0.04
    Negative Logits
     estimates
    -1.76
    cks
    -1.73
    amples
    -1.58
    oes
    -1.54
    ).)
    -1.48
     accounts
    -1.46
     precipitation
    -1.46
    iers
    -1.45
     rains
    -1.44
    oys
    -1.43
    POSITIVE LOGITS
    áĢ¯
    1.94
    áĢ¬
    1.88
    áĢº
    1.77
     luck
    1.68
     Syndrome
    1.67
     patient
    1.63
    wegian
    1.61
     onclick
    1.58
     loved
    1.57
     prostate
    1.52
    Activations Density 1.889%

    No Known Activations