© 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. 25378
    Prev
    Next
    INDEX
    Explanations

    "NOTICE" sections in documents

    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
    443
    +0.11
    0.6%
    15
    +0.11
    0.6%
    150
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.11
    0.01
    15
    +0.11
    0.01
    361
    +0.10
    0.01
    Negative Logits
    uclear
    -1.73
    upon
    -1.70
     distance
    -1.62
    cled
    -1.62
     moonlight
    -1.57
     reckon
    -1.56
     ever
    -1.49
    omitempty
    -1.46
    ucleotide
    -1.45
    atinib
    -1.44
    POSITIVE LOGITS
    Ļª
    1.77
    Ĭ
    1.74
    eries
    1.70
    etto
    1.62
    rooms
    1.59
     era
    1.58
    ivism
    1.57
    ressor
    1.52
    ivist
    1.52
    imento
    1.52
    Activations Density 0.182%

    No Known Activations