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

    Neuronpedia

    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. 27143
    Prev
    Next
    INDEX
    Explanations

    commentary or documentation notes in code

    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
    485
    +0.14
    0.8%
    32
    +0.14
    0.8%
    262
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    225
    +0.14
    0.02
    295
    +0.14
    0.02
    403
    +0.11
    0.02
    Negative Logits
     wondered
    -1.57
     Wiley
    -1.54
     pending
    -1.52
     synthase
    -1.51
     examiner
    -1.42
     remotely
    -1.42
     digest
    -1.41
    ytes
    -1.41
     lik
    -1.40
    leigh
    -1.38
    POSITIVE LOGITS
    ĸ
    3.21
    Ľ
    3.01
    Į
    2.90
    ĵ
    2.88
    ŀ
    2.84
    ĺ
    2.82
    į
    2.82
    Īĺ
    2.79
    Ĺ
    2.79
    ½
    2.73
    Activations Density 1.560%

    No Known Activations