© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 29301
    Prev
    Next
    INDEX
    Explanations

    multiple instances of the word "popup" or code-related references

    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
    195
    +0.12
    0.7%
    102
    +0.11
    0.6%
    363
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.12
    0.11
    371
    +0.11
    0.12
    18
    +0.11
    0.08
    Negative Logits
    pered
    -1.79
    ige
    -1.74
    ÃŁe
    -1.73
    ffic
    -1.67
    ulic
    -1.63
    aque
    -1.62
    )](#
    -1.48
    aid
    -1.46
    Äĩ
    -1.46
    ean
    -1.44
    POSITIVE LOGITS
    tons
    1.55
     care
    1.50
     rights
    1.42
     oversight
    1.40
    uries
    1.37
    mente
    1.30
     horiz
    1.29
     aspart
    1.24
    ización
    1.24
    prises
    1.24
    Activations Density 0.283%

    No Known Activations