© 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. 0-MLP-SM
    11. 26312
    Prev
    Next
    INDEX
    Explanations

    instances of the word "action."

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    505
    +0.16
    0.9%
    376
    +0.15
    0.9%
    219
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    505
    +0.16
    0.05
    158
    +0.15
    0.04
    336
    +0.13
    0.04
    Negative Logits
     anything
    -1.84
     ever
    -1.75
    ounder
    -1.68
     BGCOLOR
    -1.67
     her
    -1.65
     hers
    -1.59
     privileged
    -1.58
     his
    -1.57
    ollowing
    -1.51
     what
    -1.51
    POSITIVE LOGITS
    naire
    1.98
    maps
    1.84
    cards
    1.84
    isters
    1.79
    cript
    1.75
    piece
    1.73
    Ãł
    1.73
    guns
    1.72
    ais
    1.69
    film
    1.68
    Activations Density 0.324%

    No Known Activations