© 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. 31125
    Prev
    Next
    INDEX
    Explanations

    occurrences of measurements in kilometers

    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
    405
    +0.12
    0.7%
    499
    +0.11
    0.7%
    397
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.12
    0.01
    347
    +0.11
    0.01
    405
    +0.11
    0.01
    Negative Logits
    cing
    -1.63
     stomach
    -1.55
     authors
    -1.54
    schem
    -1.53
     slightest
    -1.51
    sing
    -1.50
    cause
    -1.44
    cess
    -1.44
    hing
    -1.42
    hentication
    -1.41
    POSITIVE LOGITS
    ĻĤ
    3.42
    Į
    3.11
    į
    3.06
    Ł
    3.03
    ĩ
    2.91
    ¶
    2.77
    ¸
    2.74
    ·
    2.72
    Ĵ
    2.71
    ħ
    2.69
    Activations Density 0.022%

    No Known Activations