© 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. 30337
    Prev
    Next
    INDEX
    Explanations

    references to COVID-19 and related discussions on its impact

    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
    71
    +0.13
    0.7%
    111
    +0.13
    0.7%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.01
    71
    +0.13
    0.01
    240
    +0.12
    0.01
    Negative Logits
    Ļª
    -2.67
    ¸
    -2.56
    ¼
    -2.53
    ĸ´
    -2.52
    µ
    -2.45
    ¿
    -2.43
    ·¸
    -2.36
    ¹
    -2.33
    ¿½
    -2.29
    ľ
    -2.28
    POSITIVE LOGITS
    ariate
    2.62
    arian
    1.81
    entry
    1.64
    ulent
    1.64
     references
    1.63
    estone
    1.59
    genstein
    1.59
    fefe
    1.58
    assic
    1.56
    iral
    1.55
    Activations Density 0.285%

    No Known Activations