© 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. 0-MLP-SM
    11. 26852
    Prev
    Next
    INDEX
    Explanations

    the term "instance" in various contexts

    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
    392
    +0.13
    0.8%
    247
    +0.13
    0.8%
    391
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    371
    +0.13
    0.02
    307
    +0.13
    0.02
    245
    +0.13
    0.02
    Negative Logits
    ·¸
    -3.23
    ľ
    -3.20
    Ĥ¬
    -2.98
    ·
    -2.90
    ľĵ
    -2.88
    ī
    -2.85
    Ľ
    -2.79
    Ĩ
    -2.70
    Ļª
    -2.67
    ı
    -2.63
    POSITIVE LOGITS
    iliary
    1.87
    tion
    1.73
     arsenal
    1.71
    sheet
    1.64
    oft
    1.59
    mann
    1.56
     sheet
    1.56
    ography
    1.51
     Instruments
    1.50
     notebook
    1.49
    Activations Density 1.636%

    No Known Activations