© 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. 27052
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the prominence or significance of various subjects

    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
    15
    +0.14
    0.8%
    404
    +0.13
    0.7%
    372
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.14
    0.06
    372
    +0.13
    0.03
    306
    +0.12
    0.04
    Negative Logits
    yst
    -1.65
    Ń
    -1.61
    ĵ
    -1.57
    Ĺ
    -1.56
    Ħ
    -1.52
    ³
    -1.50
    IJ
    -1.49
    ł
    -1.46
    į
    -1.38
    isor
    -1.38
    POSITIVE LOGITS
    bring
    1.44
    gage
    1.43
    legate
    1.34
    aggio
    1.29
    agne
    1.28
    bows
    1.28
    rics
    1.27
    loo
    1.26
    stairs
    1.26
     clicked
    1.25
    Activations Density 0.450%

    No Known Activations