© 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. 24001
    Prev
    Next
    INDEX
    Explanations

    instances of high levels of busyness or activity

    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
    396
    +0.12
    0.7%
    8
    +0.11
    0.6%
    84
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    155
    +0.12
    0.08
    8
    +0.11
    0.05
    277
    +0.11
    0.07
    Negative Logits
    Ł
    -1.82
    ½
    -1.62
    Ĵ
    -1.61
    į
    -1.59
      ↵
    -1.50
    -1.50
    ↵
    -1.50
    -1.50
    <|outofrange|>
    -1.50
    -1.50
    POSITIVE LOGITS
     unanimously
    1.53
    \":
    1.48
    **~
    1.37
     duck
    1.31
    MP
    1.25
    cil
    1.23
     $${\
    1.23
     solely
    1.20
    POL
    1.20
     insign
    1.20
    Activations Density 1.274%

    No Known Activations