© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28488
    Prev
    Next
    INDEX
    Explanations

    references to anime and manga

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    330
    +0.16
    0.9%
    71
    +0.14
    0.8%
    458
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.16
    0.01
    71
    +0.14
    0.01
    26
    +0.12
    0.01
    Negative Logits
      ↵
    -1.85
     heterozyg
    -1.59
     alleged
    -1.54
     elected
    -1.51
     observed
    -1.46
     vaccinated
    -1.43
     Respondent
    -1.40
     leased
    -1.39
    ödinger
    -1.39
     choosing
    -1.39
    POSITIVE LOGITS
    asek
    2.11
    recht
    1.88
    erate
    1.85
    pora
    1.80
    helf
    1.73
    works
    1.68
    eme
    1.68
    opan
    1.67
    ems
    1.66
    ulate
    1.62
    Activations Density 0.011%

    No Known Activations