© 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. 27121
    Prev
    Next
    INDEX
    Explanations

    references to fractions and informal representations of food items, particularly fried foods

    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
    +0.13
    0.8%
    100
    +0.11
    0.6%
    361
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.13
    0.00
    361
    +0.11
    0.01
    24
    +0.11
    0.01
    Negative Logits
    ¯
    -3.49
    ±
    -3.48
    ĨĴ
    -3.24
    ¼
    -3.18
    ·
    -3.12
    Ń
    -3.06
    Ĵ
    -3.04
    ©
    -2.99
    ½
    -2.98
    Īĺ
    -2.96
    POSITIVE LOGITS
    etica
    1.88
    itious
    1.85
    imate
    1.75
    igent
    1.73
    ionale
    1.72
    works
    1.69
    forge
    1.65
    ergy
    1.64
    pora
    1.62
    esan
    1.62
    Activations Density 0.011%

    No Known Activations