© 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. 25023
    Prev
    Next
    INDEX
    Explanations

    the word "sometimes" indicating occasional occurrences or variability

    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%
    94
    +0.11
    0.6%
    280
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    94
    +0.13
    0.02
    280
    +0.11
    0.03
    257
    +0.11
    0.03
    Negative Logits
    ove
    -1.68
    etted
    -1.64
    odor
    -1.55
    enium
    -1.55
    elles
    -1.52
    illard
    -1.51
     **
    -1.48
    eted
    -1.46
     slate
    -1.45
    unk
    -1.45
    POSITIVE LOGITS
    chitz
    2.22
     miracles
    1.44
    cology
    1.40
     accompanies
    1.39
    )|^
    1.38
    "])
    1.38
    itzerland
    1.38
     suffice
    1.37
    '])
    1.36
    imon
    1.35
    Activations Density 0.013%

    No Known Activations