© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 25753
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, specifically periods at the end of sentences

    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
    138
    +0.12
    0.7%
    455
    +0.11
    0.6%
    39
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.12
    0.02
    251
    +0.11
    0.03
    417
    +0.11
    0.03
    Negative Logits
    ')\
    -1.50
    '))
    -1.50
    rif
    -1.46
     remedies
    -1.43
    oxygen
    -1.42
    ')$
    -1.38
    ilate
    -1.38
    oil
    -1.35
    ))$
    -1.33
    yards
    -1.32
    POSITIVE LOGITS
    Ĥ
    2.03
    Ĥ¬
    2.00
    ĥ
    1.85
    ¾
    1.85
    ģ
    1.79
    ¿½
    1.78
    ¦
    1.72
    ł
    1.70
    Ŀ
    1.64
    ļ
    1.61
    Activations Density 0.094%

    No Known Activations