© 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. 28327
    Prev
    Next
    INDEX
    Explanations

    instances of the word "obtained."

    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
    376
    +0.20
    1.1%
    317
    +0.12
    0.7%
    351
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.20
    0.02
    254
    +0.12
    0.02
    509
    +0.12
    0.01
    Negative Logits
    ī
    -1.94
    ¼
    -1.78
    uality
    -1.71
    ĩ
    -1.67
    ĥ½
    -1.66
    Į
    -1.65
    ubot
    -1.58
    Ī
    -1.57
    Ń
    -1.57
    sson
    -1.54
    POSITIVE LOGITS
     rid
    1.41
     shelter
    1.39
     peek
    1.39
     unbiased
    1.37
     anter
    1.37
    riz
    1.36
     snap
    1.30
     frontier
    1.30
     poster
    1.29
     refuge
    1.29
    Activations Density 0.311%

    No Known Activations