© 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. 25112
    Prev
    Next
    INDEX
    Explanations

    instances of the identifier "id" followed by a value of 10

    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
    468
    +0.12
    0.7%
    326
    +0.11
    0.6%
    348
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.05
    468
    +0.11
    0.04
    161
    +0.11
    0.04
    Negative Logits
    ights
    -1.64
    IGHT
    -1.59
     pupils
    -1.58
     trier
    -1.55
     answer
    -1.46
     properly
    -1.43
     essence
    -1.43
    swers
    -1.42
     recognise
    -1.40
     anything
    -1.38
    POSITIVE LOGITS
    º
    1.94
    ensch
    1.75
    Åij
    1.73
    irectional
    1.69
    etes
    1.69
    ios
    1.68
    ég
    1.66
    FW
    1.65
    ée
    1.61
    yll
    1.60
    Activations Density 0.037%

    No Known Activations