© 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. 25717
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and similar punctuation marks in a code snippet context

    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
    427
    +0.14
    0.8%
    421
    +0.13
    0.7%
    127
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.14
    0.06
    50
    +0.13
    0.03
    206
    +0.13
    0.02
    Negative Logits
    .^\[[@
    -1.78
    ^[@
    -1.78
     LIABLE
    -1.73
    [@
    -1.68
    ^\[[@
    -1.63
     subdivision
    -1.57
    .^[@
    -1.55
    paces
    -1.54
    plasty
    -1.54
    PropertyGroup
    -1.53
    POSITIVE LOGITS
    ĻĤ
    2.37
    ¤
    2.21
    ľ
    2.15
    Ļ
    2.08
    ¼
    1.97
    Ĺ
    1.94
     shows
    1.85
    ĩ
    1.82
    ĥ
    1.71
    °
    1.70
    Activations Density 0.361%

    No Known Activations