© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-MLP-SM
    11. 26892
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "did" and its various forms

    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
    196
    +0.11
    0.6%
    104
    +0.10
    0.5%
    166
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.11
    0.20
    47
    +0.10
    0.14
    152
    +0.10
    0.14
    Negative Logits
    Ĩ
    -2.18
    IJ
    -2.05
    İ
    -1.83
    Ģ
    -1.80
    ł
    -1.76
    ½
    -1.66
    Ĥ
    -1.60
    ŀ
    -1.59
    ĨĴ
    -1.51
     enough
    -1.50
    POSITIVE LOGITS
    arant
    1.71
    iest
    1.64
    romycin
    1.57
    ubicin
    1.49
     lives
    1.49
    phrine
    1.49
    chen
    1.48
    ---|---|---
    1.48
    oside
    1.47
     couples
    1.45
    Activations Density 0.490%

    No Known Activations