© 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. 30644
    Prev
    Next
    INDEX
    Explanations

    the concept of efficiency in various contexts

    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
    1.6%
    376
    +0.20
    1.1%
    255
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    255
    +0.28
    0.01
    393
    +0.20
    0.01
    300
    +0.10
    0.01
    Negative Logits
    teenth
    -1.62
    fold
    -1.55
    ff
    -1.52
    arl
    -1.51
    ureus
    -1.50
    ller
    -1.46
    son
    -1.46
    anan
    -1.46
    abel
    -1.43
    older
    -1.43
    POSITIVE LOGITS
     enough
    2.00
    enron
    1.50
     Xin
    1.36
     CCT
    1.30
     coincidence
    1.27
     -->
    1.26
     speaking
    1.25
     SIM
    1.23
     pleased
    1.22
     shutting
    1.22
    Activations Density 0.193%

    No Known Activations