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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26387
    Prev
    Next
    INDEX
    Explanations

    specific years or dates mentioned in the text

    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
    429
    +0.16
    0.9%
    364
    +0.15
    0.8%
    471
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.16
    0.04
    364
    +0.15
    0.03
    316
    +0.12
    0.04
    Negative Logits
    urally
    -1.77
    elijk
    -1.75
    edly
    -1.65
    ionale
    -1.56
    ures
    -1.45
     dating
    -1.43
    uria
    -1.40
    ently
    -1.40
     quo
    -1.40
    uring
    -1.40
    POSITIVE LOGITS
    ĨĴ
    1.87
    ¢
    1.83
    ł
    1.69
    ¦
    1.67
    ĻĤ
    1.61
    Ĵ
    1.49
    Ļª
    1.49
    ¨
    1.48
    roup
    1.48
    Ĭ
    1.48
    Activations Density 0.078%

    No Known Activations