© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 26859
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "to"

    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
    43
    +0.13
    0.7%
    16
    +0.13
    0.7%
    160
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.05
    109
    +0.13
    0.04
    434
    +0.13
    0.04
    Negative Logits
    £
    -1.85
    ¢
    -1.49
     whether
    -1.47
    ±
    -1.44
    noreply
    -1.42
    ĸ´
    -1.40
    µ
    -1.39
    )](#
    -1.38
    «
    -1.37
     younger
    -1.36
    POSITIVE LOGITS
    mium
    1.79
    adium
    1.62
    ove
    1.55
     notation
    1.54
     wraps
    1.49
     heels
    1.49
    oster
    1.48
    culus
    1.48
    wire
    1.48
    ima
    1.47
    Activations Density 0.028%

    No Known Activations