© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 28082
    Prev
    Next
    INDEX
    Explanations

    references to surgical procedures involving incisions

    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%
    376
    +0.16
    0.9%
    316
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.28
    0.01
    232
    +0.16
    0.01
    316
    +0.14
    0.01
    Negative Logits
     fois
    -1.73
    unnumbered
    -1.62
    MOESM
    -1.48
     publish
    -1.45
     participating
    -1.44
     publication
    -1.31
     particular
    -1.29
     Publ
    -1.27
     dass
    -1.26
     toda
    -1.22
    POSITIVE LOGITS
    istan
    1.61
    ulent
    1.56
     amounts
    1.53
     limits
    1.52
    istani
    1.50
     banking
    1.50
    istor
    1.50
    imeter
    1.50
    bank
    1.49
    )].
    1.45
    Activations Density 0.017%

    No Known Activations