© 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. 28296
    Prev
    Next
    INDEX
    Explanations

    phrases related to opportunities and options

    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
    +0.28
    1.7%
    262
    +0.15
    0.9%
    376
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.28
    0.02
    424
    +0.15
    0.01
    495
    +0.13
    0.01
    Negative Logits
    ĥ½
    -3.35
    §
    -3.14
    »
    -2.56
    ¿
    -2.54
    ĵ
    -2.50
    ©
    -2.35
    į
    -2.28
    ¼
    -2.25
    İ
    -2.17
    ±
    -2.13
    POSITIVE LOGITS
    hell
    1.85
     directions
    1.68
     horiz
    1.50
     lane
    1.50
    hole
    1.49
     aren
    1.46
    pace
    1.42
    ante
    1.37
    acting
    1.36
    illar
    1.34
    Activations Density 0.024%

    No Known Activations