© 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. 24932
    Prev
    Next
    INDEX
    Explanations

    punctuation marks or closing brackets that indicate the end of sentences or citations

    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
    23
    +0.59
    4.4%
    258
    +0.24
    1.7%
    156
    +0.17
    1.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.59
    0.09
    23
    +0.24
    0.07
    271
    +0.17
    0.03
    Negative Logits
    ÅĽci
    -2.36
    =”
    -2.02
    haus
    -2.02
    idav
    -1.94
    rooms
    -1.90
    ista
    -1.90
    room
    -1.88
    endas
    -1.86
     edition
    -1.86
    ière
    -1.84
    POSITIVE LOGITS
    then
    1.78
     sudden
    1.75
    rap
    1.68
    rapeutic
    1.68
    ushed
    1.61
    xiety
    1.61
     Then
    1.60
     gentle
    1.60
     finally
    1.60
     loose
    1.59
    Activations Density 5.176%

    No Known Activations