© 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. 24381
    Prev
    Next
    INDEX
    Explanations

    legal references and citations

    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
    156
    +0.14
    0.8%
    225
    +0.13
    0.7%
    467
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    467
    +0.14
    0.03
    386
    +0.13
    0.02
    280
    +0.10
    0.02
    Negative Logits
     acres
    -1.76
     cents
    -1.56
     Wiley
    -1.55
     hereby
    -1.53
     placebo
    -1.41
     earnings
    -1.33
     exhib
    -1.32
     Weekly
    -1.32
     Nevada
    -1.32
     Miller
    -1.31
    POSITIVE LOGITS
     deployed
    1.69
    Äĩ
    1.64
    InstanceState
    1.64
    bootstrap
    1.62
    dock
    1.57
    chitz
    1.56
    example
    1.43
     invented
    1.43
     encounter
    1.42
    effect
    1.40
    Activations Density 0.094%

    No Known Activations