© 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. 30595
    Prev
    Next
    INDEX
    Explanations

    the term "called."

    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
    58
    +0.13
    0.7%
    511
    +0.12
    0.7%
    332
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    33
    +0.13
    0.04
    51
    +0.12
    0.04
    331
    +0.12
    0.04
    Negative Logits
    ings
    -1.77
    ittings
    -1.74
    itudes
    -1.72
    ides
    -1.70
    iders
    -1.64
    ientes
    -1.63
    heries
    -1.60
    ives
    -1.54
    ients
    -1.51
    ;</
    -1.49
    POSITIVE LOGITS
    ======
    1.58
     anybody
    1.45
     tons
    1.41
    CHANTABILITY
    1.38
     parity
    1.37
    baum
    1.37
    googleapis
    1.37
     anyone
    1.33
    apolis
    1.33
    AH
    1.30
    Activations Density 0.020%

    No Known Activations