© 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. 28223
    Prev
    Next
    INDEX
    Explanations

    the word "while" in various contexts

    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
    231
    +0.14
    0.8%
    8
    +0.13
    0.7%
    114
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    104
    +0.14
    0.07
    106
    +0.13
    0.06
    496
    +0.11
    0.06
    Negative Logits
    edly
    -1.52
     renewed
    -1.46
     attention
    -1.44
     Osw
    -1.44
     abroad
    -1.42
     vigorously
    -1.41
     together
    -1.33
     endeav
    -1.33
    ursuant
    -1.32
    urop
    -1.32
    POSITIVE LOGITS
    ¨
    2.08
    º
    1.74
    ¡
    1.72
    ¿½
    1.72
    ¢
    1.67
    «
    1.64
    iddle
    1.59
    1.59
    ↵↵
    1.59
    1.59
    Activations Density 0.039%

    No Known Activations