© 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. 24929
    Prev
    Next
    INDEX
    Explanations

    terms related to obstruction or restriction

    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
    +0.16
    0.9%
    408
    +0.12
    0.6%
    94
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.16
    0.01
    231
    +0.12
    0.01
    94
    +0.11
    0.01
    Negative Logits
     celebrated
    -1.78
    ITC
    -1.75
    Argued
    -1.72
    isted
    -1.71
    woke
    -1.68
    LLOW
    -1.58
    ised
    -1.53
    herty
    -1.53
    >`
    -1.51
    '>
    -1.49
    POSITIVE LOGITS
    ĻĤ
    1.88
    ÃŃs
    1.88
     violates
    1.50
     malf
    1.48
    ammers
    1.48
    gap
    1.47
    yard
    1.44
    quet
    1.43
    abolic
    1.42
    oque
    1.40
    Activations Density 0.017%

    No Known Activations