© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26948
    Prev
    Next
    INDEX
    Explanations

    coding and programming-related terminology

    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
    +0.22
    1.2%
    192
    +0.13
    0.7%
    469
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.22
    0.08
    56
    +0.13
    0.09
    474
    +0.13
    0.03
    Negative Logits
    gery
    -1.71
    inary
    -1.51
    stract
    -1.42
    Module
    -1.42
    aukee
    -1.34
     successfully
    -1.33
    obic
    -1.33
    local
    -1.32
    ocy
    -1.32
    usiness
    -1.31
    POSITIVE LOGITS
     era
    1.91
    rah
    1.60
     onward
    1.50
     rap
    1.41
     shud
    1.41
     eyed
    1.38
     inspiration
    1.37
     cord
    1.36
    century
    1.35
     Era
    1.35
    Activations Density 1.045%

    No Known Activations