© 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. 2-MLP-SM
    11. 23813
    Prev
    Next
    INDEX
    Explanations

    numeric values and statistical data

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.16
    0.9%
    410
    +0.15
    0.8%
    298
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.16
    0.04
    497
    +0.15
    0.01
    313
    +0.09
    0.02
    Negative Logits
    »¿
    -2.67
    ĩ
    -2.60
    Ļª
    -2.49
    ı
    -2.47
     ↵
    -2.46
    ↵  ³³³
    -2.46
    -2.46
    ↵
    -2.46
    č↵
    -2.46
    ↵
    -2.46
    POSITIVE LOGITS
    ”)
    1.69
     haste
    1.62
     grievances
    1.61
     tense
    1.56
     contempt
    1.56
     disple
    1.53
    !)
    1.52
     mistake
    1.51
    stituted
    1.50
     apology
    1.49
    Activations Density 0.216%

    No Known Activations