© 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. 2-MLP-SM
    11. 22495
    Prev
    Next
    INDEX
    Explanations

    numeric values and associated modifiers in various contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    23
    +0.15
    0.9%
    292
    +0.12
    0.7%
    377
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.15
    0.06
    377
    +0.12
    0.07
    332
    +0.11
    0.09
    Negative Logits
     Adm
    -1.35
     Update
    -1.34
     Room
    -1.34
     Guy
    -1.34
    eval
    -1.33
    lining
    -1.32
    ème
    -1.32
     360
    -1.32
     DL
    -1.32
    posts
    -1.31
    POSITIVE LOGITS
     hers
    1.75
    ĥ½
    1.73
    "?
    1.71
    overty
    1.54
     luck
    1.49
    thood
    1.48
    "];
    1.48
    plasia
    1.46
    odend
    1.41
    genesis
    1.40
    Activations Density 2.364%

    No Known Activations