© 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. 26386
    Prev
    Next
    INDEX
    Explanations

    config definitions and attributes in programming 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
    217
    +0.15
    0.8%
    156
    +0.13
    0.7%
    188
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.15
    0.12
    187
    +0.13
    0.03
    217
    +0.11
    0.12
    Negative Logits
    »¿
    -1.70
    ¿
    -1.69
    hips
    -1.65
    Ļª
    -1.62
    ritis
    -1.61
    leys
    -1.60
    ¼
    -1.56
    ↵↵
    -1.55
    -1.55
    ↵
    -1.55
    POSITIVE LOGITS
    etermined
    1.63
     probability
    1.61
    ``
    1.61
    idyl
    1.55
    ose
    1.53
     parameter
    1.50
    operated
    1.43
     errno
    1.43
     proposed
    1.36
     manifold
    1.35
    Activations Density 1.487%

    No Known Activations