© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 30872
    Prev
    Next
    INDEX
    Explanations

    phrases related to collection

    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
    232
    +0.13
    0.7%
    234
    +0.13
    0.7%
    42
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    494
    +0.13
    0.45
    209
    +0.13
    0.29
    402
    +0.12
    0.26
    Negative Logits
     bills
    -1.48
     Caribbean
    -1.43
    head
    -1.38
    acetic
    -1.37
     tolerant
    -1.35
    lands
    -1.35
     Europeans
    -1.33
    gut
    -1.31
     Canadians
    -1.30
    ylum
    -1.28
    POSITIVE LOGITS
    "}](#
    1.99
    ¦
    1.88
    ite
    1.81
    ·
    1.79
    ¨
    1.75
    ¯
    1.75
    ':
    1.73
    ĭ
    1.72
    ©
    1.67
    ³
    1.65
    Activations Density 1.578%

    No Known Activations