© 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. 2-MLP-SM
    11. 23314
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, especially commas

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    223
    +0.12
    0.7%
    253
    +0.12
    0.6%
    207
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.12
    0.02
    223
    +0.12
    0.02
    207
    +0.11
    0.02
    Negative Logits
     BGCOLOR
    -1.63
    ³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³³
    -1.56
    enron
    -1.52
    ">&
    -1.51
    encephal
    -1.45
    ↵↵
    -1.45
    ">"
    -1.43
     href
    -1.43
    >()
    -1.41
     xmlns
    -1.40
    POSITIVE LOGITS
    Īĺ
    2.84
    IJ
    2.73
    ĸ
    2.57
    ĵ
    2.52
    ¾
    2.44
    ļ
    2.42
    Ĵ
    2.41
    Ŀ
    2.37
    ĺ
    2.33
    ª
    2.25
    Activations Density 0.035%

    No Known Activations