© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23293
    Prev
    Next
    INDEX
    Explanations

    references to data structures and elements 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
    111
    +0.57
    4.2%
    156
    +0.44
    3.3%
    56
    +0.09
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    138
    +0.57
    0.05
    381
    +0.44
    0.04
    66
    +0.09
    0.04
    Negative Logits
    ®
    -5.87
    ↵
    -5.47
    č↵
    -5.47
             ↵
    -5.47
    ↵
    -5.47
    -5.47
     ↵
    -5.47
    ↵
    -5.47
    ↵
    -5.47
    -5.47
    POSITIVE LOGITS
    TRODUCTION
    1.55
     those
    1.54
     old
    1.43
     others
    1.34
     them
    1.30
     myself
    1.28
     anything
    1.25
    ison
    1.24
     somewhere
    1.23
    others
    1.21
    Activations Density 0.054%

    No Known Activations