© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 25948
    Prev
    Next
    INDEX
    Explanations

    elements related to programming syntax, specifically function and class definitions

    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
    156
    +0.19
    1.1%
    23
    +0.16
    0.9%
    92
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.19
    0.02
    405
    +0.16
    0.06
    327
    +0.13
    0.08
    Negative Logits
    mitt
    -1.61
    holm
    -1.59
     orders
    -1.52
    recht
    -1.49
    umar
    -1.44
    ström
    -1.41
    heim
    -1.38
    endor
    -1.35
    dern
    -1.32
    etin
    -1.31
    POSITIVE LOGITS
    ľĵ
    2.20
    ¿
    2.18
    Īĺ
    2.08
    ±
    2.06
    ĥ
    1.95
    Ĥ
    1.95
    Ĥ¬
    1.94
    ¡
    1.90
    Ŀ
    1.90
    »
    1.85
    Activations Density 1.910%

    No Known Activations