© 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. 30882
    Prev
    Next
    INDEX
    Explanations

    advertisement-related content

    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
    376
    +0.13
    0.7%
    355
    +0.12
    0.7%
    301
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    355
    +0.13
    0.02
    483
    +0.12
    0.02
    419
    +0.11
    0.02
    Negative Logits
    ¯
    -1.89
     ")
    -1.70
    Ĺ
    -1.70
    aphyl
    -1.68
    ?)
    -1.62
    xico
    -1.61
     ">
    -1.57
    ĺ
    -1.51
    İ
    -1.51
    ))?
    -1.48
    POSITIVE LOGITS
    ieux
    1.94
    GFP
    1.81
    ![(
    1.74
    inous
    1.69
    zilla
    1.57
    hoc
    1.57
    vance
    1.56
    ulent
    1.55
    obe
    1.51
    less
    1.50
    Activations Density 0.010%

    No Known Activations