© 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. 0-MLP-SM
    11. 28913
    Prev
    Next
    INDEX
    Explanations

    instances of emphasis or exclamation

    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
    172
    +0.11
    0.6%
    498
    +0.09
    0.5%
    170
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    76
    +0.11
    0.06
    190
    +0.09
    0.05
    418
    +0.09
    0.05
    Negative Logits
    ership
    -1.73
     purposes
    -1.60
    abbath
    -1.50
    DEX
    -1.49
    onian
    -1.46
    ticos
    -1.45
     duty
    -1.42
    ET
    -1.39
    olution
    -1.37
    elles
    -1.37
    POSITIVE LOGITS
    iba
    1.73
    =/
    1.56
    ©
    1.52
     await
    1.46
     Birds
    1.41
    fy
    1.40
     Chapman
    1.38
     DOI
    1.34
    ¢
    1.31
    IJ
    1.29
    Activations Density 0.044%

    No Known Activations