© 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. 24742
    Prev
    Next
    INDEX
    Explanations

    instances of the term "whether."

    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
    238
    +0.13
    0.7%
    406
    +0.12
    0.6%
    492
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.13
    0.03
    406
    +0.12
    0.04
    266
    +0.11
    0.02
    Negative Logits
     duty
    -1.44
     light
    -1.37
     heat
    -1.36
     subjective
    -1.35
    ational
    -1.35
     conflicts
    -1.34
     disbelief
    -1.34
     dark
    -1.33
    irm
    -1.30
     tent
    -1.29
    POSITIVE LOGITS
    »¿
    2.25
    hops
    1.82
    mouth
    1.78
    Inflater
    1.71
    bows
    1.71
    doibase
    1.66
    hop
    1.65
    forge
    1.62
    .
    1.57
     @@
    1.56
    Activations Density 0.135%

    No Known Activations