© 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. 0-MLP-SM
    11. 26984
    Prev
    Next
    INDEX
    Explanations

    terms related to atomic properties in programming or data structures

    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/0-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.0.hook_mlp_out
    Hook Layer
    0
    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
    126
    +0.11
    0.7%
    300
    +0.11
    0.6%
    71
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.11
    0.01
    300
    +0.11
    0.01
    149
    +0.11
    0.01
    Negative Logits
    acular
    -1.75
    forth
    -1.70
     own
    -1.58
     usual
    -1.53
     entire
    -1.52
     said
    -1.50
     any
    -1.46
    omitempty
    -1.38
     complete
    -1.37
    GREEK
    -1.36
    POSITIVE LOGITS
    "}](#
    1.91
    burg
    1.83
    ism
    1.81
    ities
    1.77
    hole
    1.71
    arters
    1.67
    bay
    1.65
    endar
    1.63
    istics
    1.63
    istic
    1.60
    Activations Density 0.012%

    No Known Activations