© 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. 2-MLP-SM
    11. 23313
    Prev
    Next
    INDEX
    Explanations

    instances of the word "named."

    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
    428
    +0.12
    0.7%
    127
    +0.11
    0.6%
    311
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    311
    +0.12
    0.03
    428
    +0.11
    0.02
    281
    +0.11
    0.01
    Negative Logits
     period
    -1.84
     periods
    -1.70
     fields
    -1.69
     method
    -1.66
     phases
    -1.60
     signature
    -1.60
     systematic
    -1.58
     childhood
    -1.56
     methods
    -1.54
     journals
    -1.54
    POSITIVE LOGITS
    rots
    1.75
    pite
    1.75
    liv
    1.74
    $).
    1.73
    onsense
    1.72
    ols
    1.72
    ))$.
    1.69
    akin
    1.67
    genstein
    1.67
    oppel
    1.65
    Activations Density 0.318%

    No Known Activations