© 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. 25240
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "suffered" and its variants, which indicate distress or hardship

    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
    376
    +0.17
    0.9%
    125
    +0.11
    0.6%
    451
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    96
    +0.17
    0.02
    215
    +0.11
    0.02
    451
    +0.11
    0.01
    Negative Logits
     USA
    -1.43
    District
    -1.42
     District
    -1.36
    Cole
    -1.31
     evalu
    -1.31
    ĵ
    -1.31
    United
    -1.30
    UTERS
    -1.28
    ĥ½
    -1.28
     United
    -1.25
    POSITIVE LOGITS
    án
    1.70
    aneous
    1.60
    ont
    1.54
    ible
    1.53
    imal
    1.49
     apart
    1.48
    river
    1.47
    !(
    1.46
    raid
    1.45
    ienn
    1.45
    Activations Density 0.009%

    No Known Activations