© 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. 26390
    Prev
    Next
    INDEX
    Explanations

    references to unspecified but significant concepts or ideas

    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
    +0.15
    0.8%
    408
    +0.13
    0.8%
    367
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.15
    0.06
    179
    +0.13
    0.07
    367
    +0.11
    0.06
    Negative Logits
    §
    -2.33
    ¥
    -2.28
    µ
    -2.19
    ¦
    -2.05
    ĸ
    -2.03
    ĨĴ
    -2.01
    ı
    -1.97
    ·¸
    -1.95
    ´
    -1.86
    ±
    -1.85
    POSITIVE LOGITS
     deficit
    1.89
     resembling
    1.83
     else
    1.81
    ULAR
    1.62
    aliana
    1.59
    documentclass
    1.58
     sclerosis
    1.55
     brighter
    1.51
    uclear
    1.42
    iological
    1.39
    Activations Density 0.157%

    No Known Activations