© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 25159
    Prev
    Next
    INDEX
    Explanations

    references to global warming and its implications

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    376
    +0.13
    0.7%
    274
    +0.12
    0.7%
    242
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    242
    +0.13
    0.01
    270
    +0.12
    0.01
    329
    +0.11
    0.01
    Negative Logits
    ı
    -2.71
    Ĥ
    -2.63
    Ŀ
    -2.50
    ¿
    -2.46
    ĥ½
    -2.43
    İ
    -2.21
    ľĵ
    -2.14
    ĭ
    -2.09
    Ĭ
    -2.05
    ¿½
    -2.03
    POSITIVE LOGITS
    ist
    1.82
    ales
    1.72
    ilee
    1.69
    Variables
    1.64
    holds
    1.55
    hold
    1.54
    ives
    1.52
     policy
    1.44
     relies
    1.41
     episode
    1.41
    Activations Density 0.008%

    No Known Activations