© 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. 22850
    Prev
    Next
    INDEX
    Explanations

    references to military divisions and their operations

    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
    148
    +0.15
    0.8%
    478
    +0.14
    0.8%
    271
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.15
    0.12
    148
    +0.14
    0.07
    235
    +0.12
    0.09
    Negative Logits
    ters
    -1.99
    guards
    -1.74
    resses
    -1.73
    rs
    -1.71
    lies
    -1.71
    gers
    -1.67
    ges
    -1.64
    mits
    -1.61
    pires
    -1.57
    urers
    -1.56
    POSITIVE LOGITS
    3.13
    3.13
    ↵
    3.13
    <|outofrange|>
    3.13
    ↵
    3.13
    ↵
    3.13
    ↵↵
    3.13
      ↵
    3.13
    ↵
    3.13
    <|outofrange|>
    3.13
    Activations Density 1.488%

    No Known Activations