© 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. 26516
    Prev
    Next
    INDEX
    Explanations

    articles 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
    405
    +0.13
    0.8%
    459
    +0.13
    0.7%
    33
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    496
    +0.13
    0.04
    33
    +0.13
    0.03
    476
    +0.12
    0.04
    Negative Logits
     WARRANTIES
    -1.62
     peroxide
    -1.52
    oda
    -1.52
     ourselves
    -1.47
     acids
    -1.45
    oxin
    -1.42
     morphine
    -1.41
    UTION
    -1.41
     judgments
    -1.38
    ness
    -1.36
    POSITIVE LOGITS
    ↵
    4.52
     ↵
    4.52
              ↵
    4.52
    ↵
    4.52
           ↵
    4.52
    4.52
                  ↵
    4.52
             ↵
    4.52
    ↵
    4.52
    ↵  âĢĥ
    4.52
    Activations Density 0.146%

    No Known Activations