© 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. 25296
    Prev
    Next
    INDEX
    Explanations

    references to limousines and their services

    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
    +0.12
    0.6%
    59
    +0.11
    0.6%
    111
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    157
    +0.12
    0.01
    355
    +0.11
    0.01
    435
    +0.11
    0.01
    Negative Logits
     thee
    -1.66
    FPar
    -1.63
     thou
    -1.60
     entire
    -1.57
     slightest
    -1.55
    looking
    -1.54
     forthcoming
    -1.51
     mothers
    -1.47
     former
    -1.45
     host
    -1.43
    POSITIVE LOGITS
    estone
    2.15
    estones
    2.10
    ĻĤ
    1.79
    ioni
    1.78
    enium
    1.72
    pective
    1.68
    ue
    1.67
    agne
    1.66
    etti
    1.64
    ī
    1.61
    Activations Density 0.009%

    No Known Activations