© 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. 24925
    Prev
    Next
    INDEX
    Explanations

    references to an audience or groups of people

    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
    156
    +0.15
    0.9%
    126
    +0.15
    0.9%
    72
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.15
    0.03
    72
    +0.15
    0.02
    0
    +0.13
    0.02
    Negative Logits
    ĥ½
    -3.39
    ĥ
    -3.23
    ³
    -3.22
    ĻĤ
    -3.21
    ı
    -3.10
    Ĥ
    -3.08
    ij
    -3.04
    IJ
    -3.00
    -2.97
    ↵Č
    -2.97
    POSITIVE LOGITS
    imetry
    1.92
    ional
    1.82
    itud
    1.74
    zione
    1.66
    ctic
    1.63
    piece
    1.59
     feedback
    1.58
    ive
    1.58
    illar
    1.57
    imeter
    1.54
    Activations Density 0.198%

    No Known Activations