© 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. 29091
    Prev
    Next
    INDEX
    Explanations

    the term "counterpart" in various contexts, highlighting comparative relationships

    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
    +0.17
    1.0%
    376
    +0.16
    0.9%
    268
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    268
    +0.17
    0.01
    487
    +0.16
    0.01
    241
    +0.14
    0.01
    Negative Logits
    ĥ½
    -4.25
    Ĵ
    -3.99
    į
    -3.90
    ħ
    -3.89
     ↵
    -3.88
    -3.88
    -3.88
    č↵
    -3.88
    ↵
    -3.88
    ↵
    -3.88
    POSITIVE LOGITS
    pace
    2.19
    ystems
    1.95
    hole
    1.90
    cript
    1.86
    hot
    1.77
    imal
    1.70
    GPU
    1.62
    hold
    1.58
    Culture
    1.55
    holes
    1.54
    Activations Density 0.021%

    No Known Activations