© 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. 2-MLP-SM
    11. 24941
    Prev
    Next
    INDEX
    Explanations

    numerical representations related to sizes or quantities

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    +0.29
    1.6%
    293
    +0.13
    0.7%
    316
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.29
    0.01
    467
    +0.13
    0.01
    293
    +0.12
    0.02
    Negative Logits
    oun
    -1.54
     inventors
    -1.44
     editors
    -1.39
     consumers
    -1.39
    inary
    -1.34
    ERTYPE
    -1.34
    irector
    -1.33
     learners
    -1.32
    oxford
    -1.32
    opyright
    -1.30
    POSITIVE LOGITS
    enron
    1.57
    gas
    1.55
    lies
    1.48
     nearby
    1.42
     grounds
    1.39
     leave
    1.38
     supplies
    1.34
    gem
    1.34
     helping
    1.31
    nia
    1.31
    Activations Density 0.128%

    No Known Activations