© 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. 27964
    Prev
    Next
    INDEX
    Explanations

    instances of the word "automatic."

    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%
    148
    +0.15
    0.9%
    156
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.20
    0.02
    340
    +0.15
    0.01
    404
    +0.12
    0.01
    Negative Logits
    rog
    -1.51
    llo
    -1.50
    rie
    -1.42
    au
    -1.39
    rs
    -1.39
    rea
    -1.37
    lla
    -1.34
    rier
    -1.33
    affin
    -1.33
    ugen
    -1.33
    POSITIVE LOGITS
    º
    3.42
    µ
    3.09
    ĸ
    3.04
    Īĺ
    3.03
    ĻĤ
    2.98
    Ģ
    2.92
    ¨
    2.80
    ¾
    2.80
    ¯
    2.79
    ķ
    2.76
    Activations Density 0.264%

    No Known Activations