© 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 EvalsExportsinterp-engineNEWAPI 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. 25782
    Prev
    Next
    INDEX
    Explanations

    references to the number "hundred."

    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
    499
    +0.15
    0.8%
    156
    +0.13
    0.7%
    434
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    499
    +0.15
    0.02
    297
    +0.13
    0.01
    70
    +0.11
    0.01
    Negative Logits
    ICA
    -1.74
    ICAL
    -1.54
    RENT
    -1.49
    IC
    -1.48
    utz
    -1.46
    ICAN
    -1.45
    rien
    -1.43
     Society
    -1.43
    UNC
    -1.41
    ULTS
    -1.41
    POSITIVE LOGITS
    ¸
    2.83
    ®
    2.81
    Ļ
    2.77
    «
    2.72
    ķ
    2.71
    ħ
    2.71
    ª
    2.63
    ģ
    2.62
    ¥
    2.61
    ¡
    2.54
    Activations Density 0.051%

    No Known Activations