© 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. 29563
    Prev
    Next
    INDEX
    Explanations

    words associated with unsustainability and associated negative implications

    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
    214
    +0.15
    0.9%
    180
    +0.15
    0.8%
    369
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.15
    0.02
    180
    +0.15
    0.02
    375
    +0.15
    0.02
    Negative Logits
    backs
    -2.12
     backs
    -1.69
    ments
    -1.69
    ment
    -1.61
    ttes
    -1.55
    ees
    -1.52
    tion
    -1.51
    ting
    -1.47
     halves
    -1.47
     glu
    -1.45
    POSITIVE LOGITS
    µ
    2.94
    ¤
    2.72
    ²
    2.71
    Ī
    2.67
    Ĥ¬
    2.62
    ĺ
    2.57
    Īĺ
    2.56
    ·¸
    2.53
    ·
    2.50
    Ł
    2.46
    Activations Density 0.011%

    No Known Activations