© 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. 27019
    Prev
    Next
    INDEX
    Explanations

    recurring phrases or repeated elements in text

    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
    270
    +0.14
    0.8%
    28
    +0.13
    0.7%
    406
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.36
    23
    +0.13
    0.31
    494
    +0.12
    0.25
    Negative Logits
    Ħ
    -3.77
    ĥ½
    -3.70
    ¬
    -3.64
    ¿
    -3.64
    ·
    -3.56
    ĩ
    -3.54
    Ĭ
    -3.51
    ¨
    -3.50
    Īĺ
    -3.49
    ij
    -3.45
    POSITIVE LOGITS
    elijk
    1.88
    ':
    1.69
     me
    1.55
    unnumbered
    1.51
    elij
    1.48
    ussen
    1.46
     frustrated
    1.44
     verbose
    1.40
    watson
    1.40
     agg
    1.39
    Activations Density 3.067%

    No Known Activations