© 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. 2-MLP-SM
    11. 22398
    Prev
    Next
    INDEX
    Explanations

    instances of emotive expressions or sentiment-related phrases

    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/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
    Neuron Alignment
    Index
    Value
    % of L₁
    391
    +0.11
    0.6%
    221
    +0.11
    0.6%
    463
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.11
    0.07
    391
    +0.11
    0.08
    164
    +0.10
    0.07
    Negative Logits
    odies
    -1.81
    ently
    -1.55
    rieved
    -1.43
    êm
    -1.37
     science
    -1.36
     lovers
    -1.35
     amateur
    -1.33
    izumab
    -1.33
     occasion
    -1.31
    blogger
    -1.30
    POSITIVE LOGITS
    ŀ
    2.95
    °
    2.74
    ¼
    2.65
    ±
    2.60
    £
    2.59
    ij
    2.58
    Ń
    2.57
    İ
    2.56
    ĥ
    2.52
    ¿
    2.51
    Activations Density 0.208%

    No Known Activations