© 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. 2-MLP-SM
    11. 24988
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases that suggest multi-faceted or complex scenarios

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    104
    +0.14
    0.8%
    23
    +0.13
    0.7%
    307
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    313
    +0.14
    0.01
    104
    +0.13
    0.02
    242
    +0.13
    0.02
    Negative Logits
    ás
    -1.82
    enso
    -1.75
    elo
    -1.72
    aned
    -1.72
    ogh
    -1.68
    ák
    -1.61
    owing
    -1.56
    iska
    -1.56
    ientes
    -1.56
    ocom
    -1.55
    POSITIVE LOGITS
    ı
    4.40
    ª
    4.14
    ľ
    4.10
    ŀ
    4.05
    ·
    4.03
    Ŀ
    3.98
    ¢
    3.92
    ĩ
    3.91
    Ļ
    3.91
    ¨
    3.90
    Activations Density 0.038%

    No Known Activations