© 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. 26063
    Prev
    Next
    INDEX
    Explanations

    instances of documentation or references related to healthcare regulations and events

    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
    305
    +0.12
    0.7%
    83
    +0.12
    0.7%
    452
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.12
    0.36
    23
    +0.12
    0.31
    494
    +0.12
    0.25
    Negative Logits
    ·¸
    -1.89
    ĵ
    -1.75
     jeopardy
    -1.74
    ¶
    -1.66
    ĸ´
    -1.59
    ı
    -1.57
    ľ
    -1.57
    ¦
    -1.56
    ¯
    -1.55
    ↵
    -1.54
    POSITIVE LOGITS
     tunes
    1.59
    atics
    1.53
     noise
    1.51
    rowave
    1.49
    ature
    1.48
    oth
    1.46
    naire
    1.43
    ches
    1.43
    amm
    1.42
    oby
    1.42
    Activations Density 3.082%

    No Known Activations