© 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. 25922
    Prev
    Next
    INDEX
    Explanations

    instances of the word "only."

    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
    396
    +0.15
    0.9%
    372
    +0.13
    0.7%
    91
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    128
    +0.15
    0.09
    409
    +0.13
    0.09
    207
    +0.13
    0.09
    Negative Logits
    ¯
    -3.05
    ĨĴ
    -2.77
    ¬
    -2.75
    ¨
    -2.64
    ı
    -2.58
    -2.57
    ↵
    -2.57
    č↵
    -2.57
             ↵
    -2.57
    č↵
    -2.57
    POSITIVE LOGITS
    AFFIRMED
    1.41
     scratch
    1.40
    ---|
    1.36
    ramento
    1.35
     providers
    1.33
    reads
    1.32
    heets
    1.31
     provider
    1.29
    容
    1.28
    heter
    1.27
    Activations Density 0.071%

    No Known Activations