© 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 EvalsExportsinterp-engineNEWAPI 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. 26648
    Prev
    Next
    INDEX
    Explanations

    the term "au."

    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
    43
    +0.15
    0.9%
    142
    +0.13
    0.7%
    241
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.15
    0.03
    142
    +0.13
    0.02
    499
    +0.11
    0.02
    Negative Logits
     '%
    -1.71
    )$)
    -1.66
    ^](#
    -1.61
      ↵
    -1.60
     ?"
    -1.46
     '</
    -1.46
     '')
    -1.44
    otox
    -1.43
    growth
    -1.42
    \%
    -1.41
    POSITIVE LOGITS
    ville
    1.76
    ppo
    1.73
    clair
    1.71
    velt
    1.66
    ethe
    1.65
    borg
    1.62
    pere
    1.60
    gary
    1.57
    vin
    1.54
    owa
    1.53
    Activations Density 0.015%

    No Known Activations