© 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. 29827
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the word "work."

    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
    54
    +0.14
    0.8%
    193
    +0.12
    0.7%
    253
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.14
    0.07
    347
    +0.12
    0.06
    117
    +0.11
    0.07
    Negative Logits
    omy
    -1.95
     convict
    -1.54
     permission
    -1.44
    attention
    -1.44
     elegans
    -1.44
     murdered
    -1.44
     womb
    -1.43
     kills
    -1.40
     ')
    -1.39
     vou
    -1.36
    POSITIVE LOGITS
    ¢
    3.78
    Ļª
    3.73
    ľ
    3.69
    ŀ
    3.64
    ī
    3.62
    Ĵ
    3.49
    Ľ
    3.42
    »¿
    3.38
    Ļ
    3.33
    ķ
    3.23
    Activations Density 0.053%

    No Known Activations