© 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 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. 28889
    Prev
    Next
    INDEX
    Explanations

    references to "night."

    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
    477
    +0.14
    0.8%
    376
    +0.12
    0.7%
    318
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    374
    +0.14
    0.05
    288
    +0.12
    0.04
    477
    +0.11
    0.04
    Negative Logits
    ľĵ
    -2.94
    Ŀ
    -2.75
    ¡
    -2.66
    ĥ
    -2.63
    Ľ
    -2.53
    ĺ
    -2.52
    Ĩ
    -2.51
    ĸ´
    -2.50
    ķ
    -2.49
    ĥ½
    -2.46
    POSITIVE LOGITS
    mares
    2.18
    dream
    1.97
    ingale
    1.94
    ongs
    1.94
    walker
    1.93
    mare
    1.86
    lights
    1.84
    craft
    1.75
    cano
    1.75
    birds
    1.73
    Activations Density 0.027%

    No Known Activations