© 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 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. 24595
    Prev
    Next
    INDEX
    Explanations

    phrases that pertain to programming concepts and 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/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
    184
    +0.15
    0.8%
    187
    +0.12
    0.7%
    275
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.15
    0.03
    141
    +0.12
    0.08
    455
    +0.11
    0.07
    Negative Logits
    noreply
    -2.13
     consequences
    -1.71
    rowser
    -1.64
    ozy
    -1.63
    ennes
    -1.57
    oqu
    -1.57
    actic
    -1.55
    iska
    -1.49
    uscript
    -1.47
    ittings
    -1.46
    POSITIVE LOGITS
    2.76
    ↵
    2.76
    ↵
    2.76
     ↵
    2.76
    ↵
    2.76
    ↵
    2.76
    ↵↵↵
    2.76
    ↵
    2.76
    2.76
    ↵↵
    2.76
    Activations Density 1.685%

    No Known Activations