© 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. 27987
    Prev
    Next
    INDEX
    Explanations

    the term "Red."

    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
    369
    +0.15
    0.9%
    385
    +0.12
    0.7%
    474
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.15
    0.02
    187
    +0.12
    0.01
    1
    +0.11
    0.01
    Negative Logits
    ĸ´
    -2.41
    Ĺ
    -2.24
    ĭ
    -1.96
     hers
    -1.87
    Ĥ¬
    -1.84
    Ĩ
    -1.79
    ĥ½
    -1.75
    ı
    -1.72
    rapeut
    -1.70
    ·¸
    -1.69
    POSITIVE LOGITS
    charts
    1.91
    skins
    1.90
    ibase
    1.73
    fall
    1.73
     Rapids
    1.72
    minded
    1.72
    icum
    1.70
    dit
    1.69
    leaf
    1.68
    grass
    1.66
    Activations Density 0.014%

    No Known Activations