© 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. 25872
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "number"

    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
    287
    +0.16
    0.9%
    144
    +0.12
    0.7%
    496
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.16
    0.07
    496
    +0.12
    0.06
    222
    +0.12
    0.05
    Negative Logits
     whichever
    -1.59
     nature
    -1.54
     none
    -1.52
     court
    -1.48
     commission
    -1.47
     even
    -1.40
     Social
    -1.38
     any
    -1.37
     close
    -1.37
     totally
    -1.36
    POSITIVE LOGITS
    hoe
    2.08
    esis
    1.88
    oft
    1.64
    cript
    1.58
    nier
    1.58
    ily
    1.52
    kerchief
    1.51
     hur
    1.50
    bourg
    1.49
    etting
    1.46
    Activations Density 0.681%

    No Known Activations