© 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. 24936
    Prev
    Next
    INDEX
    Explanations

    the term "explicit" and its variants

    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
    111
    +0.14
    0.8%
    177
    +0.13
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.01
    177
    +0.13
    0.01
    429
    +0.11
    0.01
    Negative Logits
    hib
    -1.58
    rian
    -1.56
    rians
    -1.54
    mt
    -1.54
    hip
    -1.51
    illed
    -1.50
    unnumbered
    -1.50
    astern
    -1.46
    ynchron
    -1.46
    NdEx
    -1.45
    POSITIVE LOGITS
    __.
    1.76
    amente
    1.69
     ingredients
    1.66
    lege
    1.65
    ÃŃs
    1.64
     ingredient
    1.62
    ariate
    1.59
    bay
    1.58
    caster
    1.57
    ière
    1.51
    Activations Density 0.012%

    No Known Activations