© 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. 24935
    Prev
    Next
    INDEX
    Explanations

    the word "Gent" 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/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
    410
    +0.16
    0.9%
    130
    +0.13
    0.8%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.01
    111
    +0.13
    0.01
    347
    +0.12
    0.01
    Negative Logits
     birth
    -1.72
     different
    -1.64
     sex
    -1.56
     its
    -1.52
     gentle
    -1.47
    cludes
    -1.44
     nerve
    -1.44
     sexual
    -1.43
     her
    -1.43
     _________
    -1.42
    POSITIVE LOGITS
    lemen
    2.06
    ^](#
    1.84
    "}](#
    1.84
    leman
    1.76
    ilee
    1.73
    icult
    1.73
    ibase
    1.70
    oo
    1.62
    loo
    1.60
    wine
    1.59
    Activations Density 0.016%

    No Known Activations