© 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. 30726
    Prev
    Next
    INDEX
    Explanations

    URIs or links in the text

    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
    509
    +0.14
    0.8%
    176
    +0.11
    0.6%
    478
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    509
    +0.14
    0.08
    101
    +0.11
    0.06
    0
    +0.10
    0.06
    Negative Logits
    )](#
    -1.94
    )](
    -1.56
     rule
    -1.56
     (`
    -1.49
    icated
    -1.45
     Include
    -1.44
    ](#
    -1.42
    ](
    -1.38
     version
    -1.37
     Zo
    -1.35
    POSITIVE LOGITS
    ĥ½
    2.62
    ĵ
    2.59
    ĨĴ
    2.44
    ĸ´
    2.43
    ·¸
    2.38
    IJ
    2.37
    Ĩ
    2.31
    ¼
    2.25
    Į
    2.23
    »¿
    2.14
    Activations Density 0.087%

    No Known Activations