© 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. 25670
    Prev
    Next
    INDEX
    Explanations

    instances of the word "a" 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/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
    476
    +0.15
    0.9%
    496
    +0.13
    0.7%
    170
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    476
    +0.15
    0.07
    509
    +0.13
    0.04
    480
    +0.13
    0.05
    Negative Logits
     derivatives
    -1.50
     cop
    -1.45
     mixtures
    -1.44
     interchange
    -1.38
    ational
    -1.35
    orphic
    -1.31
    GIN
    -1.30
    orphisms
    -1.30
    rapeutics
    -1.30
     clear
    -1.28
    POSITIVE LOGITS
              ↵
    2.29
    ↵
    2.29
    č↵
    2.29
    ↵
    2.29
    ↵
    2.29
    č↵
    2.29
    2.29
    <|outofrange|>
    2.29
    ↵
    2.29
    ↵
    2.29
    Activations Density 0.813%

    No Known Activations