© 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. 26492
    Prev
    Next
    INDEX
    Explanations

    references to academic or scientific research

    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
    156
    +0.14
    0.8%
    365
    +0.13
    0.7%
    376
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.14
    0.03
    356
    +0.13
    0.03
    331
    +0.12
    0.03
    Negative Logits
    ¯
    -2.78
    §
    -2.47
    ĥ½
    -2.36
    Į
    -2.29
    IJ
    -2.23
    ĨĴ
    -2.10
    ¿
    -2.05
    ©
    -2.00
    ī
    -2.00
    ı
    -1.96
    POSITIVE LOGITS
    fiddle
    2.04
    fully
    1.62
    iem
    1.59
     crop
    1.55
    yard
    1.55
    horse
    1.54
    pieces
    1.48
    tube
    1.48
    olta
    1.46
    craft
    1.46
    Activations Density 0.608%

    No Known Activations