© 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. 28172
    Prev
    Next
    INDEX
    Explanations

    the presence of specific sequences or structures in the data

    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
    224
    +0.13
    0.7%
    89
    +0.12
    0.7%
    207
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    354
    +0.13
    0.07
    381
    +0.12
    0.06
    247
    +0.12
    0.06
    Negative Logits
    º
    -3.02
    ¿½
    -3.01
    °
    -2.87
    ¥
    -2.77
    ³
    -2.74
    ©
    -2.74
    ¼
    -2.73
    ĨĴ
    -2.71
    Ł
    -2.66
    µ
    -2.62
    POSITIVE LOGITS
    ptions
    2.32
    ancies
    1.96
     Bankruptcy
    1.82
     famine
    1.61
     franch
    1.51
     slavery
    1.50
     miracles
    1.47
     corruption
    1.47
    ctions
    1.46
     Redistributions
    1.45
    Activations Density 0.059%

    No Known Activations